Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1276172 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0171. Min Act: -0.0006

Data Index: 103308 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0174. Min Act: -0.0006

Data Index: 798843 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0173. Min Act: -0.0006

Data Index: 91507 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0171. Min Act: -0.0006

Data Index: 804605 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0170. Min Act: -0.0006

Data Index: 836510 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1140243 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0173. Min Act: -0.0006

Data Index: 434459 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0167. Min Act: -0.0006

Data Index: 347351 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0166. Min Act: -0.0006

Data Index: 997646 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1098953 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0163. Min Act: -0.0006

Data Index: 874223 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0163. Min Act: -0.0007

Data Index: 693663 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0163. Min Act: -0.0006

Data Index: 431383 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0162. Min Act: -0.0006

Data Index: 976992 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0162. Min Act: -0.0005

Data Index: 907050 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0162. Min Act: -0.0006

Data Index: 815367 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0162. Min Act: -0.0006

Data Index: 531222 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1284069 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0161. Min Act: -0.0006

Data Index: 737755 (C4 (Web Text))

Max Activating Token Index: 487