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

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

Neuron 3386 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: 0.6310. Min Range: -0.6310

Max Act: 0.6310. Min Act: 0.0000

Data Index: 434129 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1031045 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5299. Min Act: -0.0000

Data Index: 717833 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1040012 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5619. Min Act: -0.0001

Data Index: 2037 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5219. Min Act: -0.0000

Data Index: 937898 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4632. Min Act: -0.0000

Data Index: 2277 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4395. Min Act: -0.0000

Data Index: 941236 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1216590 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4330. Min Act: -0.0000

Data Index: 187348 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4416. Min Act: -0.0000

Data Index: 792522 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4416. Min Act: -0.0000

Data Index: 924486 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4244. Min Act: -0.0000

Data Index: 847649 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4330. Min Act: -0.0001

Data Index: 1007977 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1078842 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1082479 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1012709 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4169. Min Act: -0.0000

Data Index: 529952 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4204. Min Act: -0.0000

Data Index: 706918 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.3960. Min Act: -0.0001

Data Index: 637133 (C4 (Web Text))

Max Activating Token Index: 201