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

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

Neuron 3346 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1018927 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3390. Min Act: -0.0001

Data Index: 8471 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3311. Min Act: -0.0000

Data Index: 302565 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3742. Min Act: -0.0000

Data Index: 464146 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1327239 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1164842 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3414. Min Act: -0.0000

Data Index: 30834 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3368. Min Act: -0.0001

Data Index: 1006880 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3239. Min Act: -0.0000

Data Index: 683274 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1343855 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3218. Min Act: -0.0000

Data Index: 986689 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3435. Min Act: -0.0000

Data Index: 150797 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3299. Min Act: -0.0000

Data Index: 126121 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3222. Min Act: -0.0000

Data Index: 264387 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3200. Min Act: -0.0001

Data Index: 190041 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3218. Min Act: -0.0000

Data Index: 277638 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3191. Min Act: -0.0000

Data Index: 368849 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1320467 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.2939. Min Act: -0.0000

Data Index: 75050 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1302789 (C4 (Web Text))

Max Activating Token Index: 839