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

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

Neuron 5372 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.5820. Min Act: -0.0001

Data Index: 735160 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3654. Min Act: -0.0001

Data Index: 1265474 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.4105. Min Act: -0.0001

Data Index: 80690 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3894. Min Act: -0.0001

Data Index: 1183493 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3399. Min Act: -0.0001

Data Index: 578846 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.4603. Min Act: -0.0001

Data Index: 73347 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.2536. Min Act: -0.0001

Data Index: 1265885 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.1466. Min Act: -0.0001

Data Index: 499302 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.1694. Min Act: -0.0001

Data Index: 146147 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 3.5820. Min Range: -3.5820

Max Act: 2.9874. Min Act: -0.0001

Data Index: 494771 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.1253. Min Act: -0.0001

Data Index: 622873 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.2767. Min Act: -0.0001

Data Index: 259917 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.0725. Min Act: -0.0001

Data Index: 405698 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.0771. Min Act: -0.0001

Data Index: 1322994 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 3.5820. Min Range: -3.5820

Max Act: 2.8918. Min Act: -0.0001

Data Index: 781172 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.1749. Min Act: -0.0001

Data Index: 799468 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.0506. Min Act: -0.0001

Data Index: 11160 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.0164. Min Act: -0.0001

Data Index: 871425 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.1361. Min Act: -0.0001

Data Index: 548406 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 3.5820. Min Range: -3.5820

Max Act: 2.7995. Min Act: -0.0001

Data Index: 1087939 (C4 (Web Text))

Max Activating Token Index: 613