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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4703 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.9306. Min Act: -0.0000

Data Index: 1200905 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.8020. Min Act: -0.0000

Data Index: 909469 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.6977. Min Act: -0.0000

Data Index: 610781 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.7176. Min Act: -0.0000

Data Index: 57538 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.4625. Min Act: -0.0000

Data Index: 602312 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.5338. Min Act: -0.0000

Data Index: 406669 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.5174. Min Act: -0.0000

Data Index: 998436 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.4108. Min Act: -0.0000

Data Index: 1327627 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.4157. Min Act: -0.0000

Data Index: 60554 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.3988. Min Act: -0.0000

Data Index: 275031 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.3916. Min Act: -0.0000

Data Index: 1622886 (Python Code)

Max Activating Token Index: 974

Text #11

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.5597. Min Act: -0.0000

Data Index: 1633132 (Python Code)

Max Activating Token Index: 994

Text #12

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1352991 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.4593. Min Act: -0.0000

Data Index: 397958 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.3792. Min Act: -0.0000

Data Index: 526236 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.4582. Min Act: -0.0000

Data Index: 385402 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.4404. Min Act: -0.0000

Data Index: 145626 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.4318. Min Act: -0.0000

Data Index: 1212310 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.4120. Min Act: -0.0000

Data Index: 782863 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.9306. Min Range: -1.9306

Max Act: 1.3964. Min Act: -0.0000

Data Index: 954012 (C4 (Web Text))

Max Activating Token Index: 197