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

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

Neuron 2467 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1132504 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0294. Min Act: -0.0003

Data Index: 492176 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0315. Min Act: -0.0003

Data Index: 963537 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0289. Min Act: -0.0003

Data Index: 8170 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0287. Min Act: -0.0003

Data Index: 244195 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1167587 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0277. Min Act: -0.0003

Data Index: 994210 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0297. Min Act: -0.0003

Data Index: 387924 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0302. Min Act: -0.0003

Data Index: 706179 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0296. Min Act: -0.0003

Data Index: 842789 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1332960 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0278. Min Act: -0.0003

Data Index: 716638 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0279. Min Act: -0.0003

Data Index: 429279 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0321. Min Act: -0.0003

Data Index: 785361 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0282. Min Act: -0.0003

Data Index: 299947 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0270. Min Act: -0.0003

Data Index: 367671 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0271. Min Act: -0.0003

Data Index: 688556 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0285. Min Act: -0.0003

Data Index: 716845 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1215648 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0285. Min Act: -0.0004

Data Index: 918796 (C4 (Web Text))

Max Activating Token Index: 493