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

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

Neuron 1572 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0005

Data Index: 357863 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0203. Min Act: -0.0005

Data Index: 1173557 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0170. Min Act: -0.0005

Data Index: 1519844 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1293908 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0200. Min Act: -0.0005

Data Index: 316881 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0167. Min Act: -0.0005

Data Index: 904846 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0155. Min Act: -0.0005

Data Index: 652028 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0161. Min Act: -0.0005

Data Index: 393367 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0167. Min Act: -0.0005

Data Index: 860178 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0161. Min Act: -0.0005

Data Index: 455851 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0153. Min Act: -0.0005

Data Index: 1344774 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0157. Min Act: -0.0005

Data Index: 268240 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0153. Min Act: -0.0005

Data Index: 215298 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0157. Min Act: -0.0005

Data Index: 146387 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0146. Min Act: -0.0005

Data Index: 674498 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0148. Min Act: -0.0005

Data Index: 101490 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0154. Min Act: -0.0005

Data Index: 550111 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0145. Min Act: -0.0005

Data Index: 460416 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0148. Min Act: -0.0005

Data Index: 568974 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0144. Min Act: -0.0005

Data Index: 777499 (C4 (Web Text))

Max Activating Token Index: 341