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

Dataset: The Pile

Neuron 3697 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.6245. Min Act: -0.0000

Data Index: 668945 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.6664. Min Act: -0.0000

Data Index: 380157 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.7612. Min Act: -0.0000

Data Index: 754137 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.5662. Min Act: -0.0000

Data Index: 1780389 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1692103 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1371780 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.9661. Min Act: -0.0000

Data Index: 619074 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.1468. Min Act: -0.0000

Data Index: 534037 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 1.7612. Min Range: -1.7612

Max Act: 1.0419. Min Act: -0.0000

Data Index: 716423 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1383589 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1148576 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.9228. Min Act: 0.0000

Data Index: 508848 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1371698 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.8514. Min Act: -0.0000

Data Index: 400648 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1032219 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1005780 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.9441. Min Act: -0.0000

Data Index: 546191 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.8154. Min Act: -0.0000

Data Index: 207000 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.8183. Min Act: -0.0000

Data Index: 749521 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 1.7612. Min Range: -1.7612

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1003386 (The Pile)

Max Activating Token Index: 932