Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2761 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.5372. Min Act: -0.0000

Data Index: 180411 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.4263. Min Act: -0.0000

Data Index: 59236 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0936. Min Act: -0.0000

Data Index: 1261671 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1161355 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.1016. Min Act: -0.0000

Data Index: 22003 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.1678. Min Act: -0.0000

Data Index: 327855 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0141. Min Act: -0.0000

Data Index: 197474 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.0489. Min Act: -0.0000

Data Index: 3205 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1151732 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9913. Min Act: -0.0000

Data Index: 552371 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8870. Min Act: -0.0000

Data Index: 795117 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9428. Min Act: -0.0000

Data Index: 591377 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.7765. Min Act: -0.0000

Data Index: 277671 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9123. Min Act: -0.0000

Data Index: 455380 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8766. Min Act: -0.0000

Data Index: 1243916 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.7969. Min Act: -0.0000

Data Index: 797725 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1170997 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1048491 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1040400 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8192. Min Act: -0.0000

Data Index: 331717 (C4 (Web Text))

Max Activating Token Index: 905