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

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

Neuron 1027 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1298594 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1308622 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0251. Min Act: -0.0001

Data Index: 250264 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0273. Min Act: -0.0001

Data Index: 256104 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1230224 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0237. Min Act: -0.0001

Data Index: 610772 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0211. Min Act: -0.0001

Data Index: 981953 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0219. Min Act: -0.0001

Data Index: 141299 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1352784 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1541413 (Python Code)

Max Activating Token Index: 429

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1223344 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0231. Min Act: -0.0001

Data Index: 256278 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0193. Min Act: -0.0001

Data Index: 559698 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0230. Min Act: -0.0001

Data Index: 961117 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0223. Min Act: -0.0001

Data Index: 458648 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0223. Min Act: -0.0001

Data Index: 401622 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1073795 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0208. Min Act: -0.0001

Data Index: 539272 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0194. Min Act: -0.0001

Data Index: 464510 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1007849 (C4 (Web Text))

Max Activating Token Index: 249