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

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

Neuron 578 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: 1.5954. Min Range: -1.5954

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1284644 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1097814 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.3994. Min Act: -0.0000

Data Index: 616486 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2579. Min Act: -0.0000

Data Index: 228081 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 1.5954. Min Range: -1.5954

Max Act: 0.9468. Min Act: -0.0000

Data Index: 188117 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1775. Min Act: -0.0000

Data Index: 978928 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1319. Min Act: -0.0000

Data Index: 809020 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1298269 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1045163 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0644. Min Act: -0.0000

Data Index: 946505 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 1.5954. Min Range: -1.5954

Max Act: 0.9839. Min Act: -0.0000

Data Index: 63157 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1359339 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0282. Min Act: -0.0000

Data Index: 564981 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 1.5954. Min Range: -1.5954

Max Act: 0.9941. Min Act: -0.0000

Data Index: 192034 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1216036 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0784. Min Act: -0.0000

Data Index: 399576 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0057. Min Act: -0.0000

Data Index: 656969 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0226. Min Act: -0.0000

Data Index: 594252 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.5954. Min Range: -1.5954

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1170770 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.5954. Min Range: -1.5954

Max Act: 0.9016. Min Act: -0.0000

Data Index: 940026 (C4 (Web Text))

Max Activating Token Index: 870