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

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

Neuron 2675 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: 0.0201. Min Range: -0.0201

Max Act: 0.0201. Min Act: -0.0002

Data Index: 320316 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0184. Min Act: -0.0003

Data Index: 674217 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0184. Min Act: -0.0003

Data Index: 935635 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0186. Min Act: -0.0003

Data Index: 659719 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1207363 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0181. Min Act: -0.0003

Data Index: 567775 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0183. Min Act: -0.0003

Data Index: 666140 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0184. Min Act: -0.0003

Data Index: 760601 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0177. Min Act: -0.0003

Data Index: 809604 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0170. Min Act: -0.0003

Data Index: 966414 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1221048 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0165. Min Act: -0.0003

Data Index: 490147 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1107515 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0168. Min Act: -0.0003

Data Index: 794060 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1041289 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1316669 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0160. Min Act: -0.0003

Data Index: 773106 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0161. Min Act: -0.0003

Data Index: 352816 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1254804 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1227389 (C4 (Web Text))

Max Activating Token Index: 895