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

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

Neuron 3342 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.6733. Min Act: -0.0000

Data Index: 884696 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.7920. Min Act: -0.0000

Data Index: 235234 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.5028. Min Act: -0.0000

Data Index: 1239406 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.5147. Min Act: -0.0000

Data Index: 550051 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.6279. Min Act: -0.0000

Data Index: 1304110 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.4444. Min Act: -0.0000

Data Index: 783811 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.3803. Min Act: -0.0000

Data Index: 952374 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.3733. Min Act: -0.0000

Data Index: 1003433 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.3806. Min Act: -0.0000

Data Index: 1105652 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.3558. Min Act: -0.0000

Data Index: 1186571 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.2986. Min Act: -0.0000

Data Index: 537316 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.2374. Min Act: -0.0000

Data Index: 362420 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.2173. Min Act: -0.0000

Data Index: 423058 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.1074. Min Act: -0.0000

Data Index: 1011669 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.0452. Min Act: -0.0000

Data Index: 206239 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.0520. Min Act: -0.0000

Data Index: 453559 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.0977. Min Act: -0.0000

Data Index: 917763 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.0822. Min Act: -0.0000

Data Index: 501269 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.0780. Min Act: -0.0000

Data Index: 902750 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 2.7920. Min Range: -2.7920

Max Act: 2.0533. Min Act: -0.0000

Data Index: 673697 (C4 (Web Text))

Max Activating Token Index: 601