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

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

Neuron 2022 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.8641. Min Act: -0.0000

Data Index: 285226 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.9039. Min Act: -0.0000

Data Index: 121334 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.7257. Min Act: -0.0000

Data Index: 865519 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.7314. Min Act: -0.0000

Data Index: 1295842 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.6699. Min Act: -0.0000

Data Index: 1007145 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.6758. Min Act: -0.0000

Data Index: 139082 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.7579. Min Act: -0.0000

Data Index: 234953 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.3958. Min Act: -0.0000

Data Index: 339089 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.3757. Min Act: -0.0000

Data Index: 890478 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.4555. Min Act: -0.0000

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.3102. Min Act: -0.0000

Data Index: 304458 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.3084. Min Act: -0.0000

Data Index: 1631728 (Python Code)

Max Activating Token Index: 279

Text #12

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.3788. Min Act: -0.0000

Data Index: 722505 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1367021 (Python Code)

Max Activating Token Index: 584

Text #14

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.4186. Min Act: -0.0000

Data Index: 1361739 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.4883. Min Act: -0.0000

Data Index: 1376861 (Python Code)

Max Activating Token Index: 223

Text #16

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.4375. Min Act: -0.0000

Data Index: 628805 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.2979. Min Act: -0.0000

Data Index: 1150371 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1389782 (Python Code)

Max Activating Token Index: 348

Text #19

Max Range: 1.9039. Min Range: -1.9039

Max Act: 1.2609. Min Act: -0.0000

Data Index: 1067645 (C4 (Web Text))

Max Activating Token Index: 780