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

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

Neuron 1559 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: 0.0214. Min Range: -0.0214

Max Act: 0.0209. Min Act: -0.0003

Data Index: 248592 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0214. Min Act: -0.0003

Data Index: 477850 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0212. Min Act: -0.0003

Data Index: 210056 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0206. Min Act: -0.0003

Data Index: 954781 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0177. Min Act: -0.0002

Data Index: 681347 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0175. Min Act: -0.0003

Data Index: 367591 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0174. Min Act: -0.0002

Data Index: 819794 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0177. Min Act: -0.0002

Data Index: 227901 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0169. Min Act: -0.0003

Data Index: 518145 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0168. Min Act: -0.0002

Data Index: 135862 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0165. Min Act: -0.0003

Data Index: 54815 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0166. Min Act: -0.0003

Data Index: 425937 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0164. Min Act: -0.0003

Data Index: 530128 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0164. Min Act: -0.0003

Data Index: 192917 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0152. Min Act: -0.0002

Data Index: 214449 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0148. Min Act: -0.0003

Data Index: 313006 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0148. Min Act: -0.0003

Data Index: 12376 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1239916 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1189261 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1318898 (C4 (Web Text))

Max Activating Token Index: 852