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

Dataset: The Pile

Neuron 3897 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.9373. Min Act: -0.0000

Data Index: 1115489 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7287. Min Act: -0.0000

Data Index: 1755075 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7173. Min Act: -0.0000

Data Index: 318672 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.8542. Min Act: -0.0000

Data Index: 1162846 (The Pile)

Max Activating Token Index: 62

Text #4

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7393. Min Act: -0.0000

Data Index: 39482 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6513. Min Act: -0.0000

Data Index: 153476 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7127. Min Act: -0.0000

Data Index: 1289790 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7154. Min Act: -0.0000

Data Index: 993855 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6945. Min Act: -0.0000

Data Index: 111537 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7854. Min Act: -0.0000

Data Index: 1765482 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6965. Min Act: -0.0000

Data Index: 40996 (The Pile)

Max Activating Token Index: 915

Text #11

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6808. Min Act: -0.0000

Data Index: 171080 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1630121 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6775. Min Act: -0.0000

Data Index: 1722252 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6667. Min Act: -0.0000

Data Index: 142652 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6434. Min Act: -0.0000

Data Index: 1307239 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6498. Min Act: -0.0000

Data Index: 823321 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.4520. Min Act: 0.0000

Data Index: 1397241 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6389. Min Act: -0.0000

Data Index: 302005 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6396. Min Act: -0.0000

Data Index: 1591135 (The Pile)

Max Activating Token Index: 289