Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 90 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3891. Min Act: -0.0000

Data Index: 284874 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4437. Min Act: -0.0000

Data Index: 613474 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1167245 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1882 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3380. Min Act: -0.0000

Data Index: 461812 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3236. Min Act: -0.0000

Data Index: 538341 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3667. Min Act: -0.0000

Data Index: 467541 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3248. Min Act: -0.0000

Data Index: 983116 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3278. Min Act: -0.0000

Data Index: 879787 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3221. Min Act: -0.0000

Data Index: 722741 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3146. Min Act: -0.0000

Data Index: 411186 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1198113 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3060. Min Act: -0.0000

Data Index: 857344 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3126. Min Act: -0.0000

Data Index: 796453 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2966. Min Act: -0.0000

Data Index: 802836 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1193135 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1054267 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2898. Min Act: -0.0000

Data Index: 213924 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2658. Min Act: -0.0000

Data Index: 794534 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2887. Min Act: -0.0000

Data Index: 161792 (C4 (Web Text))

Max Activating Token Index: 67