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

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

Neuron 686 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1946. Min Act: -0.0002

Data Index: 570185 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1766. Min Act: -0.0003

Data Index: 508411 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1682. Min Act: -0.0003

Data Index: 1089860 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1645. Min Act: -0.0003

Data Index: 292570 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1552. Min Act: -0.0002

Data Index: 538032 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1474. Min Act: -0.0003

Data Index: 344016 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1412. Min Act: -0.0003

Data Index: 300458 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1386. Min Act: -0.0003

Data Index: 245445 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1355. Min Act: -0.0003

Data Index: 776944 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1225. Min Act: -0.0003

Data Index: 285087 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1199. Min Act: -0.0003

Data Index: 181179 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1237. Min Act: -0.0003

Data Index: 1211610 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1267. Min Act: -0.0002

Data Index: 85598 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1226. Min Act: -0.0002

Data Index: 230549 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1234. Min Act: -0.0002

Data Index: 880733 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1186. Min Act: -0.0003

Data Index: 537916 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1183. Min Act: -0.0003

Data Index: 473210 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1131. Min Act: -0.0003

Data Index: 727270 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1149. Min Act: -0.0003

Data Index: 850080 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1175. Min Act: -0.0003

Data Index: 1262823 (C4 (Web Text))

Max Activating Token Index: 191