Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3983 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8829. Min Act: -0.0000

Data Index: 938358 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8497. Min Act: -0.0000

Data Index: 480836 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1273859 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1312802 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7667. Min Act: -0.0000

Data Index: 52754 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1066008 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6992. Min Act: -0.0000

Data Index: 652446 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1073457 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1085134 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6810. Min Act: -0.0000

Data Index: 246079 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6763. Min Act: -0.0000

Data Index: 866524 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6475. Min Act: -0.0000

Data Index: 803987 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6169. Min Act: -0.0000

Data Index: 672629 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6547. Min Act: -0.0000

Data Index: 689665 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1291731 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1143876 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1079982 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5863. Min Act: 0.0000

Data Index: 409278 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6085. Min Act: -0.0000

Data Index: 294732 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1233888 (C4 (Web Text))

Max Activating Token Index: 41