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

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

Neuron 2660 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.9941. Min Act: -0.0000

Data Index: 294102 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.9157. Min Act: -0.0000

Data Index: 596115 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.9074. Min Act: -0.0000

Data Index: 592053 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8776. Min Act: -0.0001

Data Index: 1656581 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8240. Min Act: 0.0000

Data Index: 745422 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8411. Min Act: -0.0000

Data Index: 244517 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8369. Min Act: -0.0000

Data Index: 889020 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1352324 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8190. Min Act: 0.0000

Data Index: 485263 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7562. Min Act: -0.0000

Data Index: 954124 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7002. Min Act: -0.0000

Data Index: 126374 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7697. Min Act: -0.0000

Data Index: 594199 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7411. Min Act: 0.0000

Data Index: 823950 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7332. Min Act: -0.0001

Data Index: 309401 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7022. Min Act: 0.0000

Data Index: 651219 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7216. Min Act: -0.0000

Data Index: 605999 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.6971. Min Act: -0.0000

Data Index: 682412 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7463. Min Act: -0.0000

Data Index: 11898 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7291. Min Act: -0.0000

Data Index: 44482 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.6781. Min Act: -0.0001

Data Index: 339985 (C4 (Web Text))

Max Activating Token Index: 609