Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1866 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0217. Min Act: -0.0002

Data Index: 910872 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1318571 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0192. Min Act: -0.0002

Data Index: 341750 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1171340 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0214. Min Act: -0.0001

Data Index: 156899 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1493375 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0182. Min Act: -0.0001

Data Index: 703804 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0198. Min Act: -0.0001

Data Index: 592791 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0184. Min Act: -0.0001

Data Index: 35321 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0190. Min Act: -0.0001

Data Index: 413199 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1546060 (Python Code)

Max Activating Token Index: 514

Text #11

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0173. Min Act: -0.0001

Data Index: 503491 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1368318 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0195. Min Act: -0.0002

Data Index: 541903 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1094476 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0177. Min Act: -0.0002

Data Index: 713313 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0190. Min Act: -0.0002

Data Index: 887252 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1102097 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0184. Min Act: -0.0002

Data Index: 582056 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0181. Min Act: -0.0002

Data Index: 317484 (C4 (Web Text))

Max Activating Token Index: 4