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

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

Neuron 1683 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0006

Data Index: 905791 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1288435 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0170. Min Act: -0.0006

Data Index: 410814 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0168. Min Act: -0.0006

Data Index: 216332 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0162. Min Act: -0.0006

Data Index: 18614 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0168. Min Act: -0.0006

Data Index: 182967 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0167. Min Act: -0.0006

Data Index: 106272 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0166. Min Act: -0.0006

Data Index: 636209 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0159. Min Act: -0.0006

Data Index: 115875 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0154. Min Act: -0.0006

Data Index: 793046 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1173105 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1299203 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0138. Min Act: -0.0006

Data Index: 708404 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0158. Min Act: -0.0006

Data Index: 519612 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0148. Min Act: -0.0006

Data Index: 812562 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0161. Min Act: -0.0006

Data Index: 413199 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0142. Min Act: -0.0006

Data Index: 352150 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1098766 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0144. Min Act: -0.0006

Data Index: 663830 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0139. Min Act: -0.0006

Data Index: 528460 (C4 (Web Text))

Max Activating Token Index: 316