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

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

Neuron 3437 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: 0.6826. Min Range: -0.6826

Max Act: 0.6826. Min Act: -0.0001

Data Index: 1288992 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1034281 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4082. Min Act: -0.0000

Data Index: 744406 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1320147 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3695. Min Act: -0.0000

Data Index: 995838 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3186. Min Act: -0.0001

Data Index: 1422325 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1105162 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3399. Min Act: -0.0001

Data Index: 1600674 (Python Code)

Max Activating Token Index: 734

Text #8

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3607. Min Act: -0.0001

Data Index: 1490196 (Python Code)

Max Activating Token Index: 538

Text #9

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3472. Min Act: -0.0000

Data Index: 371949 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1428568 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3343. Min Act: -0.0000

Data Index: 853981 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3019. Min Act: -0.0001

Data Index: 1555482 (Python Code)

Max Activating Token Index: 454

Text #13

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1439085 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3063. Min Act: -0.0001

Data Index: 1467949 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.2937. Min Act: -0.0000

Data Index: 397439 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3082. Min Act: -0.0000

Data Index: 199543 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1436337 (Python Code)

Max Activating Token Index: 995

Text #18

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.2919. Min Act: -0.0001

Data Index: 1647278 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.2655. Min Act: -0.0001

Data Index: 1005848 (C4 (Web Text))

Max Activating Token Index: 415