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

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

Neuron 1602 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.6455. Min Act: -0.0000

Data Index: 749173 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.6418. Min Act: -0.0000

Data Index: 671733 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1113886 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5817. Min Act: -0.0001

Data Index: 588600 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5402. Min Act: -0.0000

Data Index: 3388 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4680. Min Act: -0.0000

Data Index: 869140 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4788. Min Act: -0.0000

Data Index: 829910 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4692. Min Act: -0.0000

Data Index: 578216 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4425. Min Act: -0.0000

Data Index: 691522 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4248. Min Act: -0.0000

Data Index: 18528 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1295412 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1067188 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4252. Min Act: -0.0000

Data Index: 258810 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4211. Min Act: -0.0000

Data Index: 540662 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4173. Min Act: -0.0000

Data Index: 151136 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.3897. Min Act: -0.0000

Data Index: 879122 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1041248 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4085. Min Act: -0.0001

Data Index: 64168 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4130. Min Act: -0.0000

Data Index: 211767 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4064. Min Act: -0.0000

Data Index: 26136 (C4 (Web Text))

Max Activating Token Index: 544