Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 779 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0004

Data Index: 444037 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0208. Min Act: -0.0004

Data Index: 571384 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0180. Min Act: -0.0004

Data Index: 696055 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0173. Min Act: -0.0004

Data Index: 1450482 (Python Code)

Max Activating Token Index: 651

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0170. Min Act: -0.0004

Data Index: 860014 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0171. Min Act: -0.0004

Data Index: 1323762 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0164. Min Act: -0.0004

Data Index: 765638 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0168. Min Act: -0.0004

Data Index: 457522 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0162. Min Act: -0.0004

Data Index: 856391 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0160. Min Act: -0.0004

Data Index: 612540 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0160. Min Act: -0.0004

Data Index: 1050276 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0158. Min Act: -0.0004

Data Index: 451865 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0160. Min Act: -0.0004

Data Index: 1118277 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0157. Min Act: -0.0004

Data Index: 329677 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0156. Min Act: -0.0004

Data Index: 573407 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0149. Min Act: -0.0004

Data Index: 383933 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0154. Min Act: -0.0004

Data Index: 1104852 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0150. Min Act: -0.0004

Data Index: 130677 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0150. Min Act: -0.0004

Data Index: 1045687 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0152. Min Act: -0.0004

Data Index: 1001397 (C4 (Web Text))

Max Activating Token Index: 242