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

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

Neuron 1136 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1260390 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.8252. Min Act: -0.0000

Data Index: 18739 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7518. Min Act: -0.0000

Data Index: 488760 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7409. Min Act: -0.0000

Data Index: 542413 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7393. Min Act: -0.0000

Data Index: 339215 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7321. Min Act: -0.0000

Data Index: 311280 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7543. Min Act: -0.0000

Data Index: 664263 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7165. Min Act: -0.0000

Data Index: 144650 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1248372 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7169. Min Act: -0.0000

Data Index: 2945 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7585. Min Act: -0.0000

Data Index: 681159 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7361. Min Act: -0.0001

Data Index: 306584 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7132. Min Act: -0.0000

Data Index: 109674 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.6651. Min Act: -0.0000

Data Index: 190955 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7111. Min Act: -0.0000

Data Index: 572869 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7109. Min Act: -0.0000

Data Index: 495818 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7385. Min Act: -0.0000

Data Index: 613658 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7090. Min Act: -0.0000

Data Index: 127926 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7025. Min Act: -0.0000

Data Index: 744428 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.9226. Min Range: -0.9226

Max Act: 0.7215. Min Act: -0.0000

Data Index: 439277 (C4 (Web Text))

Max Activating Token Index: 701