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

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

Neuron 1370 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.5234. Min Act: -0.0001

Data Index: 1031084 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.4675. Min Act: -0.0001

Data Index: 927789 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.4802. Min Act: -0.0001

Data Index: 8834 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.2858. Min Act: -0.0001

Data Index: 173877 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.2557. Min Act: -0.0001

Data Index: 1168649 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.2364. Min Act: -0.0001

Data Index: 627646 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.2281. Min Act: -0.0001

Data Index: 1279154 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.0925. Min Act: -0.0001

Data Index: 800721 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.1077. Min Act: -0.0001

Data Index: 453894 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.1261. Min Act: -0.0001

Data Index: 238357 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.0630. Min Act: -0.0001

Data Index: 1308911 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.0331. Min Act: -0.0001

Data Index: 1353226 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.0285. Min Act: -0.0001

Data Index: 1649683 (Python Code)

Max Activating Token Index: 127

Text #13

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.0307. Min Act: -0.0001

Data Index: 608655 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.0109. Min Act: -0.0001

Data Index: 160308 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.0583. Min Act: -0.0001

Data Index: 320051 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.0214. Min Act: -0.0001

Data Index: 391816 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 1.5234. Min Range: -1.5234

Max Act: 0.9925. Min Act: -0.0001

Data Index: 686898 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 1.5234. Min Range: -1.5234

Max Act: 1.0219. Min Act: -0.0001

Data Index: 802619 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.5234. Min Range: -1.5234

Max Act: 0.9089. Min Act: -0.0001

Data Index: 307038 (C4 (Web Text))

Max Activating Token Index: 616