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

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

Neuron 1107 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0223. Min Act: -0.0003

Data Index: 972173 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0217. Min Act: -0.0002

Data Index: 555183 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0179. Min Act: -0.0003

Data Index: 185877 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1091042 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1121750 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0165. Min Act: -0.0003

Data Index: 375462 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1210235 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0142. Min Act: -0.0003

Data Index: 723287 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0151. Min Act: -0.0003

Data Index: 975618 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0152. Min Act: -0.0003

Data Index: 363142 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0141. Min Act: -0.0003

Data Index: 11907 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0140. Min Act: -0.0003

Data Index: 844850 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0142. Min Act: -0.0003

Data Index: 316353 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0142. Min Act: -0.0003

Data Index: 615031 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0139. Min Act: -0.0003

Data Index: 252084 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1167125 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0135. Min Act: -0.0002

Data Index: 760497 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0133. Min Act: -0.0003

Data Index: 187247 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1531049 (Python Code)

Max Activating Token Index: 102

Text #19

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1058427 (C4 (Web Text))

Max Activating Token Index: 353