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

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

Neuron 3810 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: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0002

Data Index: 202258 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0170. Min Act: -0.0002

Data Index: 778178 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0163. Min Act: -0.0002

Data Index: 153715 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0153. Min Act: -0.0002

Data Index: 786366 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1188731 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0131. Min Act: -0.0002

Data Index: 618846 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0143. Min Act: -0.0002

Data Index: 460600 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0139. Min Act: -0.0002

Data Index: 95474 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1356973 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0130. Min Act: -0.0002

Data Index: 108137 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0129. Min Act: -0.0002

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0130. Min Act: -0.0002

Data Index: 328330 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1250610 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1103267 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0127. Min Act: -0.0002

Data Index: 563363 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0127. Min Act: -0.0002

Data Index: 993310 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1160438 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0124. Min Act: -0.0002

Data Index: 644516 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 178