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

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

Neuron 1344 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1440. Min Act: -0.0005

Data Index: 363517 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1337. Min Act: -0.0005

Data Index: 281876 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1324. Min Act: -0.0005

Data Index: 1028357 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1312. Min Act: -0.0005

Data Index: 804386 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1320. Min Act: -0.0005

Data Index: 1193175 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1266. Min Act: -0.0005

Data Index: 347814 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1248. Min Act: -0.0005

Data Index: 18838 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1237. Min Act: -0.0005

Data Index: 624513 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1142. Min Act: -0.0005

Data Index: 75127 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1223. Min Act: -0.0005

Data Index: 272766 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1158. Min Act: -0.0005

Data Index: 71573 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1196. Min Act: -0.0005

Data Index: 1313409 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1190. Min Act: -0.0005

Data Index: 1186204 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1184. Min Act: -0.0005

Data Index: 1711 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1147. Min Act: -0.0005

Data Index: 778570 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1171. Min Act: -0.0005

Data Index: 1213601 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1165. Min Act: -0.0005

Data Index: 1321332 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1162. Min Act: -0.0005

Data Index: 582968 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1114. Min Act: -0.0005

Data Index: 1269252 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1114. Min Act: -0.0005

Data Index: 621502 (C4 (Web Text))

Max Activating Token Index: 923