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

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

Neuron 2613 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: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0002

Data Index: 244469 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0184. Min Act: -0.0002

Data Index: 889692 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1092784 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0156. Min Act: -0.0002

Data Index: 119618 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0161. Min Act: -0.0002

Data Index: 531343 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0169. Min Act: -0.0002

Data Index: 28756 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1138096 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0144. Min Act: -0.0002

Data Index: 558956 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0148. Min Act: -0.0002

Data Index: 93931 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0138. Min Act: -0.0002

Data Index: 536111 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0141. Min Act: -0.0002

Data Index: 684228 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0135. Min Act: -0.0002

Data Index: 914735 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1153865 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1122544 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0151. Min Act: -0.0002

Data Index: 199887 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0139. Min Act: -0.0002

Data Index: 760717 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0146. Min Act: -0.0002

Data Index: 143608 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0139. Min Act: -0.0002

Data Index: 331223 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0144. Min Act: -0.0002

Data Index: 459575 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0142. Min Act: -0.0002

Data Index: 265684 (C4 (Web Text))

Max Activating Token Index: 235