Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1303 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3732. Min Act: -0.0003

Data Index: 927364 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3459. Min Act: -0.0003

Data Index: 1273457 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3275. Min Act: -0.0003

Data Index: 1654196 (Python Code)

Max Activating Token Index: 226

Text #3

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3196. Min Act: -0.0003

Data Index: 1374330 (Python Code)

Max Activating Token Index: 816

Text #4

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3407. Min Act: -0.0003

Data Index: 699564 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3389. Min Act: -0.0003

Data Index: 517295 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3004. Min Act: -0.0003

Data Index: 22038 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3213. Min Act: -0.0003

Data Index: 882906 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3100. Min Act: -0.0003

Data Index: 1227361 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3194. Min Act: -0.0003

Data Index: 652668 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3186. Min Act: -0.0003

Data Index: 542258 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3067. Min Act: -0.0003

Data Index: 1607445 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3084. Min Act: -0.0003

Data Index: 751978 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3170. Min Act: -0.0003

Data Index: 459189 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3062. Min Act: -0.0003

Data Index: 52855 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3165. Min Act: -0.0003

Data Index: 835382 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3239. Min Act: -0.0003

Data Index: 1615601 (Python Code)

Max Activating Token Index: 331

Text #17

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3203. Min Act: -0.0003

Data Index: 246353 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3102. Min Act: -0.0003

Data Index: 1305227 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3008. Min Act: -0.0003

Data Index: 302243 (C4 (Web Text))

Max Activating Token Index: 196