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

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

Neuron 1226 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0200. Min Act: -0.0006

Data Index: 715805 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0189. Min Act: -0.0006

Data Index: 302575 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1333893 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0189. Min Act: -0.0006

Data Index: 974640 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0174. Min Act: -0.0006

Data Index: 989410 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0177. Min Act: -0.0006

Data Index: 393368 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0170. Min Act: -0.0006

Data Index: 741877 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1015353 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1013770 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0178. Min Act: -0.0006

Data Index: 172135 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0165. Min Act: -0.0006

Data Index: 411314 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0167. Min Act: -0.0006

Data Index: 491738 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0174. Min Act: -0.0006

Data Index: 63776 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0165. Min Act: -0.0006

Data Index: 76625 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0164. Min Act: -0.0006

Data Index: 218936 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0171. Min Act: -0.0006

Data Index: 237921 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1037898 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0158. Min Act: -0.0006

Data Index: 900267 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0166. Min Act: -0.0006

Data Index: 475040 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1104934 (C4 (Web Text))

Max Activating Token Index: 259