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

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

Neuron 171 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: 0.1474. Min Range: -0.1474

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1312482 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1474. Min Act: -0.0000

Data Index: 118163 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1301. Min Act: -0.0000

Data Index: 738139 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1302. Min Act: -0.0000

Data Index: 501298 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1211. Min Act: -0.0000

Data Index: 209765 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1206. Min Act: -0.0000

Data Index: 596981 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1303945 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1207. Min Act: -0.0000

Data Index: 200809 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1163. Min Act: -0.0000

Data Index: 552654 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1166. Min Act: -0.0000

Data Index: 646437 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1132. Min Act: -0.0000

Data Index: 285761 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1340872 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1117. Min Act: -0.0000

Data Index: 438574 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1096907 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1269219 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1148. Min Act: -0.0000

Data Index: 184975 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1041437 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1137. Min Act: -0.0000

Data Index: 751650 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1144. Min Act: -0.0000

Data Index: 118073 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1099. Min Act: -0.0000

Data Index: 108660 (C4 (Web Text))

Max Activating Token Index: 966