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

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

Neuron 5997 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: 4.5610. Min Range: -4.5610

Max Act: 4.5610. Min Act: -0.0000

Data Index: 501006 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 4.5610. Min Range: -4.5610

Max Act: 3.2620. Min Act: -0.0000

Data Index: 995412 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 4.5610. Min Range: -4.5610

Max Act: 3.0558. Min Act: -0.0000

Data Index: 106231 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 4.5610. Min Range: -4.5610

Max Act: 3.3570. Min Act: -0.0000

Data Index: 885274 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 4.5610. Min Range: -4.5610

Max Act: 3.3412. Min Act: -0.0000

Data Index: 142508 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 4.5610. Min Range: -4.5610

Max Act: 3.2830. Min Act: -0.0000

Data Index: 450681 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 4.5610. Min Range: -4.5610

Max Act: 3.1086. Min Act: -0.0000

Data Index: 161046 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 4.5610. Min Range: -4.5610

Max Act: 3.0763. Min Act: -0.0000

Data Index: 436560 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.8751. Min Act: -0.0000

Data Index: 731817 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.7605. Min Act: -0.0000

Data Index: 655844 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.7582. Min Act: -0.0000

Data Index: 352764 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.7329. Min Act: -0.0000

Data Index: 1339005 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.7128. Min Act: -0.0000

Data Index: 1206232 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.9598. Min Act: -0.0000

Data Index: 575547 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.6849. Min Act: -0.0000

Data Index: 353788 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.6027. Min Act: -0.0000

Data Index: 1222792 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.7270. Min Act: -0.0000

Data Index: 367475 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.7062. Min Act: -0.0000

Data Index: 475718 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.5519. Min Act: -0.0000

Data Index: 1112504 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 4.5610. Min Range: -4.5610

Max Act: 2.4899. Min Act: -0.0000

Data Index: 787808 (C4 (Web Text))

Max Activating Token Index: 507