Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 494 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0004

Data Index: 220331 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0342. Min Act: -0.0004

Data Index: 685561 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0337. Min Act: -0.0004

Data Index: 1309674 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0334. Min Act: -0.0004

Data Index: 1049428 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0322. Min Act: -0.0004

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0330. Min Act: -0.0004

Data Index: 631669 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0322. Min Act: -0.0004

Data Index: 959001 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0315. Min Act: -0.0004

Data Index: 1124197 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0312. Min Act: -0.0004

Data Index: 803076 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0300. Min Act: -0.0004

Data Index: 903944 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0280. Min Act: -0.0004

Data Index: 199761 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0308. Min Act: -0.0004

Data Index: 379694 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0293. Min Act: -0.0004

Data Index: 905878 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0291. Min Act: -0.0004

Data Index: 1082731 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0298. Min Act: -0.0004

Data Index: 1335962 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0291. Min Act: -0.0004

Data Index: 843351 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0313. Min Act: -0.0004

Data Index: 137579 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0283. Min Act: -0.0004

Data Index: 824911 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0282. Min Act: -0.0004

Data Index: 1197048 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0285. Min Act: -0.0004

Data Index: 1178471 (C4 (Web Text))

Max Activating Token Index: 589