< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 29 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.6286. Min Act: -0.0000

Data Index: 754515 (The Pile)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.5152. Min Act: -0.0000

Data Index: 252924 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.4406. Min Act: -0.0000

Data Index: 1342844 (The Pile)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1584310 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.4694. Min Act: -0.0000

Data Index: 1640732 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.4784. Min Act: -0.0000

Data Index: 412383 (The Pile)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1482420 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.2093. Min Act: -0.0000

Data Index: 1040225 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.4121. Min Act: -0.0000

Data Index: 791093 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.3309. Min Act: -0.0000

Data Index: 669543 (The Pile)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1624136 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.3652. Min Act: -0.0000

Data Index: 460864 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.3663. Min Act: -0.0000

Data Index: 86103 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.3476. Min Act: -0.0000

Data Index: 1451972 (The Pile)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1162235 (The Pile)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1280067 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.2280. Min Act: -0.0000

Data Index: 26212 (The Pile)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.2900. Min Act: -0.0000

Data Index: 450422 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1780924 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1101493 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #19