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

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

Neuron 4963 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1669. Min Act: -0.0002

Data Index: 288154 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1312. Min Act: -0.0002

Data Index: 966578 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1346532 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1275. Min Act: -0.0002

Data Index: 905425 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1312. Min Act: -0.0002

Data Index: 976454 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1205. Min Act: -0.0002

Data Index: 320250 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1156. Min Act: -0.0002

Data Index: 561700 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1107. Min Act: -0.0002

Data Index: 237153 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1280. Min Act: -0.0002

Data Index: 765516 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1161. Min Act: -0.0002

Data Index: 94827 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1162. Min Act: -0.0002

Data Index: 477964 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1219. Min Act: -0.0002

Data Index: 1281321 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1188. Min Act: -0.0002

Data Index: 139007 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1157. Min Act: -0.0002

Data Index: 519190 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1105. Min Act: -0.0002

Data Index: 967811 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1191. Min Act: -0.0002

Data Index: 726988 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1140. Min Act: -0.0002

Data Index: 1254026 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1110. Min Act: -0.0002

Data Index: 714715 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1106. Min Act: -0.0002

Data Index: 344707 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1179. Min Act: -0.0002

Data Index: 420274 (C4 (Web Text))

Max Activating Token Index: 990