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

Dataset: The Pile

Neuron 2160 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: 1.0578. Min Range: -1.0578

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1601524 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8464. Min Act: -0.0000

Data Index: 24564 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8555. Min Act: -0.0000

Data Index: 37375 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8154. Min Act: -0.0000

Data Index: 279892 (The Pile)

Max Activating Token Index: 551

Text #4

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7372. Min Act: -0.0000

Data Index: 780167 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1871106 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7417. Min Act: -0.0000

Data Index: 938062 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.6986. Min Act: -0.0000

Data Index: 963792 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7341. Min Act: -0.0000

Data Index: 405337 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7283. Min Act: -0.0000

Data Index: 231056 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1045388 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1166337 (The Pile)

Max Activating Token Index: 242

Text #12

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.6680. Min Act: -0.0000

Data Index: 749224 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1243718 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7350. Min Act: -0.0000

Data Index: 533483 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1496651 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1319854 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1758353 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1855586 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1416771 (The Pile)

Max Activating Token Index: 11