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

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

Neuron 1152 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: 1.7464. Min Range: -1.7464

Max Act: 1.7464. Min Act: -0.0000

Data Index: 306396 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.5842. Min Act: -0.0000

Data Index: 680941 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.4766. Min Act: -0.0000

Data Index: 642304 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3807. Min Act: -0.0001

Data Index: 1291651 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.4845. Min Act: -0.0000

Data Index: 912518 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.4497. Min Act: -0.0001

Data Index: 1569218 (Python Code)

Max Activating Token Index: 887

Text #6

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.4239. Min Act: -0.0000

Data Index: 417622 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3750. Min Act: 0.0001

Data Index: 821223 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3466. Min Act: -0.0000

Data Index: 489030 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1127401 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3216. Min Act: -0.0001

Data Index: 1051056 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3573. Min Act: -0.0001

Data Index: 878177 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3693. Min Act: -0.0001

Data Index: 550537 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3884. Min Act: -0.0001

Data Index: 946714 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3856. Min Act: -0.0001

Data Index: 660751 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3439. Min Act: -0.0000

Data Index: 188941 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3725. Min Act: -0.0000

Data Index: 220136 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.2841. Min Act: -0.0001

Data Index: 399894 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3049. Min Act: -0.0000

Data Index: 829936 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.7464. Min Range: -1.7464

Max Act: 1.3313. Min Act: -0.0000

Data Index: 1345744 (C4 (Web Text))

Max Activating Token Index: 792