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

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

Neuron 3266 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1211715 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1216652 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3443. Min Act: -0.0000

Data Index: 961984 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1177524 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3118. Min Act: -0.0000

Data Index: 494780 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3043. Min Act: -0.0000

Data Index: 241573 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1323711 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2955. Min Act: -0.0000

Data Index: 99607 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1032967 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2651. Min Act: -0.0000

Data Index: 99453 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2527. Min Act: -0.0000

Data Index: 537720 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2757. Min Act: -0.0000

Data Index: 257460 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2634. Min Act: -0.0000

Data Index: 740385 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2507. Min Act: -0.0000

Data Index: 955107 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2486. Min Act: -0.0000

Data Index: 120408 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2569. Min Act: -0.0000

Data Index: 746497 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2553. Min Act: -0.0000

Data Index: 70440 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1301425 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2354. Min Act: -0.0000

Data Index: 599002 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1103888 (C4 (Web Text))

Max Activating Token Index: 964