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

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

Neuron 4738 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1221. Min Range: -1.1221

Max Act: 1.1221. Min Act: -0.0000

Data Index: 877889 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7644. Min Act: -0.0000

Data Index: 225299 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7338. Min Act: -0.0000

Data Index: 90020 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.6687. Min Act: -0.0000

Data Index: 266696 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1255438 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7092. Min Act: -0.0000

Data Index: 950233 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.6988. Min Act: -0.0000

Data Index: 665100 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1372480 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.5223. Min Act: -0.0000

Data Index: 163725 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.5513. Min Act: -0.0000

Data Index: 66151 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1118279 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1119307 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.5039. Min Act: -0.0000

Data Index: 567314 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1435495 (Python Code)

Max Activating Token Index: 674

Text #14

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1506889 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.5042. Min Act: -0.0000

Data Index: 662248 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.5118. Min Act: -0.0000

Data Index: 985408 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.4806. Min Act: -0.0000

Data Index: 925385 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.4777. Min Act: -0.0000

Data Index: 1441931 (Python Code)

Max Activating Token Index: 735

Text #19

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1561503 (Python Code)

Max Activating Token Index: 495