Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 67 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0264. Min Act: -0.0006

Data Index: 643486 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0239. Min Act: -0.0006

Data Index: 568811 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0233. Min Act: -0.0006

Data Index: 724153 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0227. Min Act: -0.0006

Data Index: 876667 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1010598 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0222. Min Act: -0.0006

Data Index: 113228 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0218. Min Act: -0.0006

Data Index: 922193 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0217. Min Act: -0.0006

Data Index: 276026 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1264414 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0215. Min Act: -0.0006

Data Index: 716333 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0203. Min Act: -0.0006

Data Index: 139985 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0208. Min Act: -0.0006

Data Index: 811745 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1112933 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0207. Min Act: -0.0006

Data Index: 734640 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0222. Min Act: -0.0006

Data Index: 651144 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0210. Min Act: -0.0006

Data Index: 775181 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1310119 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0203. Min Act: -0.0006

Data Index: 69766 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1065625 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0207. Min Act: -0.0006

Data Index: 308105 (C4 (Web Text))

Max Activating Token Index: 936