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

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

Neuron 4039 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: 0.3342. Min Range: -0.3342

Max Act: 0.3342. Min Act: -0.0001

Data Index: 175430 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2527. Min Act: -0.0001

Data Index: 197520 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2264. Min Act: -0.0001

Data Index: 779326 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2368. Min Act: -0.0001

Data Index: 645842 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2180. Min Act: -0.0000

Data Index: 483118 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1624575 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2177. Min Act: -0.0001

Data Index: 1588102 (Python Code)

Max Activating Token Index: 1010

Text #7

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2239. Min Act: -0.0001

Data Index: 722991 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2227. Min Act: -0.0001

Data Index: 595438 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2154. Min Act: -0.0000

Data Index: 554901 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2131. Min Act: -0.0000

Data Index: 419843 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2206. Min Act: -0.0001

Data Index: 1363951 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2153. Min Act: -0.0000

Data Index: 950415 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2056. Min Act: -0.0001

Data Index: 372381 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2011. Min Act: -0.0001

Data Index: 273146 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2009. Min Act: -0.0001

Data Index: 540848 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1644431 (Python Code)

Max Activating Token Index: 924

Text #17

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2018. Min Act: -0.0001

Data Index: 376283 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1359807 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.3342. Min Range: -0.3342

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1333945 (C4 (Web Text))

Max Activating Token Index: 43