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

Dataset: The Pile

Neuron 4517 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: 0.5137. Min Range: -0.5137

Max Act: 0.5137. Min Act: -0.0000

Data Index: 615197 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4480. Min Act: -0.0000

Data Index: 146980 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4433. Min Act: -0.0000

Data Index: 84265 (The Pile)

Max Activating Token Index: 847

Text #3

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1222395 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4068. Min Act: -0.0000

Data Index: 750405 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1886615 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3666. Min Act: -0.0000

Data Index: 546936 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3852. Min Act: -0.0000

Data Index: 972422 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3797. Min Act: -0.0000

Data Index: 74568 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1619903 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1638480 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3414. Min Act: -0.0000

Data Index: 911719 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1598982 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1169218 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3694. Min Act: -0.0000

Data Index: 498479 (The Pile)

Max Activating Token Index: 486

Text #15

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3232. Min Act: -0.0000

Data Index: 895891 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1157228 (The Pile)

Max Activating Token Index: 274

Text #17

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1053407 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3393. Min Act: -0.0000

Data Index: 312759 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3476. Min Act: -0.0000

Data Index: 923360 (The Pile)

Max Activating Token Index: 590