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

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

Neuron 509 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.8247. Min Act: -0.0002

Data Index: 441778 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.8610. Min Act: -0.0002

Data Index: 1113154 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.7155. Min Act: -0.0002

Data Index: 1014749 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.7294. Min Act: -0.0002

Data Index: 317365 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.7191. Min Act: -0.0002

Data Index: 1354240 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.6632. Min Act: -0.0002

Data Index: 727448 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5253. Min Act: -0.0002

Data Index: 68391 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.6101. Min Act: -0.0002

Data Index: 711208 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5645. Min Act: -0.0002

Data Index: 534881 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.3464. Min Act: -0.0002

Data Index: 13909 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5217. Min Act: -0.0002

Data Index: 1290441 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.6742. Min Act: -0.0002

Data Index: 1172111 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5207. Min Act: -0.0002

Data Index: 135887 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5312. Min Act: -0.0002

Data Index: 752370 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.6232. Min Act: -0.0002

Data Index: 335650 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5395. Min Act: -0.0002

Data Index: 1054093 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5454. Min Act: -0.0002

Data Index: 1083294 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5651. Min Act: -0.0002

Data Index: 313602 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5264. Min Act: -0.0002

Data Index: 979024 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.8610. Min Range: -1.8610

Max Act: 1.5623. Min Act: -0.0002

Data Index: 119789 (C4 (Web Text))

Max Activating Token Index: 13