< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 38 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.1340. Min Act: -0.0001

Data Index: 1314408 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.2507. Min Act: -0.0000

Data Index: 1817084 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.2323. Min Act: -0.0001

Data Index: 1996481 (The Pile)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.1460. Min Act: -0.0001

Data Index: 606582 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.1475. Min Act: -0.0001

Data Index: 1447147 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.1690. Min Act: -0.0001

Data Index: 1100357 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1572892 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2507. Min Range: -2.2507

Max Act: 1.9994. Min Act: -0.0001

Data Index: 1985959 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.0970. Min Act: -0.0001

Data Index: 514856 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.0157. Min Act: -0.0001

Data Index: 49287 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2507. Min Range: -2.2507

Max Act: 1.9039. Min Act: -0.0001

Data Index: 1408256 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.2313. Min Act: -0.0001

Data Index: 1952210 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.0808. Min Act: -0.0001

Data Index: 1942662 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.1072. Min Act: -0.0001

Data Index: 1810789 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.0711. Min Act: -0.0001

Data Index: 439418 (The Pile)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.0352. Min Act: -0.0000

Data Index: 113378 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.1145. Min Act: -0.0001

Data Index: 243524 (The Pile)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.0518. Min Act: -0.0001

Data Index: 1099380 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.0419. Min Act: -0.0001

Data Index: 1316740 (The Pile)

Max Activating Token Index: 197

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2507. Min Range: -2.2507

Max Act: 2.0535. Min Act: -0.0001

Data Index: 700533 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #19