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

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

Neuron 4677 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.3827. Min Act: -0.0000

Data Index: 999329 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.2140. Min Act: -0.0000

Data Index: 415582 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0711. Min Act: -0.0000

Data Index: 46512 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 1.3827. Min Range: -1.3827

Max Act: 1.0036. Min Act: -0.0000

Data Index: 525139 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.9325. Min Act: -0.0000

Data Index: 775023 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.8419. Min Act: -0.0000

Data Index: 367556 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.8405. Min Act: -0.0000

Data Index: 267122 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1257597 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.8406. Min Act: -0.0000

Data Index: 572641 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.7434. Min Act: -0.0000

Data Index: 14721 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1156689 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1145294 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.7058. Min Act: -0.0000

Data Index: 761361 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.6616. Min Act: -0.0000

Data Index: 868420 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.5299. Min Act: -0.0000

Data Index: 752343 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.5871. Min Act: -0.0000

Data Index: 191539 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.5439. Min Act: -0.0000

Data Index: 716424 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.5481. Min Act: -0.0000

Data Index: 919895 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.5572. Min Act: -0.0000

Data Index: 289180 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 1.3827. Min Range: -1.3827

Max Act: 0.5593. Min Act: -0.0000

Data Index: 217790 (C4 (Web Text))

Max Activating Token Index: 995