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

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

Neuron 418 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0181. Min Act: -0.0006

Data Index: 107991 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0197. Min Act: -0.0006

Data Index: 123051 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0182. Min Act: -0.0006

Data Index: 985385 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1012994 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0175. Min Act: -0.0006

Data Index: 676345 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0183. Min Act: -0.0006

Data Index: 715714 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0186. Min Act: -0.0006

Data Index: 806222 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0174. Min Act: -0.0006

Data Index: 703692 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1197049 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0180. Min Act: -0.0006

Data Index: 623720 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0174. Min Act: -0.0006

Data Index: 254125 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1088616 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0183. Min Act: -0.0006

Data Index: 57888 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0171. Min Act: -0.0006

Data Index: 860205 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1035412 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0178. Min Act: -0.0006

Data Index: 57630 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0173. Min Act: -0.0006

Data Index: 151331 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1075550 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0170. Min Act: -0.0006

Data Index: 723495 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1068797 (C4 (Web Text))

Max Activating Token Index: 681