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

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

Neuron 965 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: 0.2370. Min Range: -0.2370

Max Act: 0.2363. Min Act: -0.0000

Data Index: 279517 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1110284 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2266. Min Act: -0.0000

Data Index: 255281 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2191. Min Act: -0.0001

Data Index: 762732 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2194. Min Act: -0.0000

Data Index: 43148 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2370. Min Act: -0.0000

Data Index: 354133 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2199. Min Act: -0.0000

Data Index: 498536 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2011. Min Act: -0.0001

Data Index: 999393 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2079. Min Act: -0.0000

Data Index: 324817 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1059952 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1301105 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2109. Min Act: -0.0000

Data Index: 336667 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1074852 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2095. Min Act: -0.0000

Data Index: 514404 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1262676 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1824. Min Act: -0.0000

Data Index: 939354 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1923. Min Act: -0.0000

Data Index: 299945 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1077460 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1892. Min Act: -0.0000

Data Index: 609725 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1982. Min Act: -0.0000

Data Index: 586606 (C4 (Web Text))

Max Activating Token Index: 683