Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4402 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0288. Min Range: -2.0288

Max Act: 2.0288. Min Act: -0.0000

Data Index: 1213542 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.9625. Min Act: -0.0000

Data Index: 1345721 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.7094. Min Act: -0.0000

Data Index: 1222098 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.5336. Min Act: -0.0000

Data Index: 1078750 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.6815. Min Act: -0.0000

Data Index: 50268 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.2897. Min Act: -0.0000

Data Index: 303974 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.3606. Min Act: -0.0000

Data Index: 650073 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.4354. Min Act: -0.0000

Data Index: 775452 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.4208. Min Act: -0.0000

Data Index: 1203455 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.4084. Min Act: -0.0000

Data Index: 844503 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.3271. Min Act: -0.0000

Data Index: 665076 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.4833. Min Act: -0.0000

Data Index: 513514 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1083060 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.5223. Min Act: -0.0000

Data Index: 402769 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.3391. Min Act: -0.0000

Data Index: 784722 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.2654. Min Act: -0.0000

Data Index: 361174 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.2824. Min Act: -0.0000

Data Index: 306655 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.2004. Min Act: -0.0000

Data Index: 1093756 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.2354. Min Act: -0.0000

Data Index: 621648 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 2.0288. Min Range: -2.0288

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1319280 (C4 (Web Text))

Max Activating Token Index: 15