< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 46 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.4152. Min Act: -0.0001

Data Index: 1113354 (The Pile)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.4136. Min Act: -0.0001

Data Index: 461007 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3331. Min Act: -0.0001

Data Index: 1033425 (The Pile)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3469. Min Act: -0.0001

Data Index: 650661 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3395. Min Act: -0.0001

Data Index: 1999384 (The Pile)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2886. Min Act: -0.0001

Data Index: 1479743 (The Pile)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3504. Min Act: -0.0001

Data Index: 790211 (The Pile)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3019. Min Act: -0.0001

Data Index: 704765 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3662. Min Act: -0.0001

Data Index: 304242 (The Pile)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3664. Min Act: -0.0001

Data Index: 1386321 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1125597 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3406. Min Act: -0.0001

Data Index: 1045027 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3505. Min Act: -0.0001

Data Index: 928183 (The Pile)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3545. Min Act: -0.0001

Data Index: 836049 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1208200 (The Pile)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3317. Min Act: -0.0001

Data Index: 266097 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1514819 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3193. Min Act: -0.0001

Data Index: 1038599 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3290. Min Act: -0.0001

Data Index: 759703 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.4262. Min Act: -0.0001

Data Index: 1555253 (The Pile)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #19