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

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

Neuron 3990 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.4227. Min Act: -0.0000

Data Index: 702399 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.1970. Min Act: -0.0000

Data Index: 1163430 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.0727. Min Act: -0.0000

Data Index: 580687 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.9536. Min Act: -0.0000

Data Index: 555241 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 2.4227. Min Range: -2.4227

Max Act: 2.0270. Min Act: -0.0000

Data Index: 827296 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.9607. Min Act: -0.0000

Data Index: 1211342 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.8273. Min Act: -0.0000

Data Index: 486221 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.7493. Min Act: -0.0000

Data Index: 789368 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.7411. Min Act: -0.0000

Data Index: 914415 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.7028. Min Act: -0.0000

Data Index: 742633 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.6957. Min Act: -0.0000

Data Index: 966410 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.6003. Min Act: -0.0000

Data Index: 3532 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.6725. Min Act: -0.0000

Data Index: 920872 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.6795. Min Act: -0.0000

Data Index: 1302366 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.5579. Min Act: -0.0000

Data Index: 982094 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.7470. Min Act: -0.0000

Data Index: 196075 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1031611 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.6925. Min Act: -0.0000

Data Index: 820752 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.5884. Min Act: -0.0000

Data Index: 403970 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 2.4227. Min Range: -2.4227

Max Act: 1.5742. Min Act: -0.0000

Data Index: 460246 (C4 (Web Text))

Max Activating Token Index: 399