Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 937 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.8507. Min Act: -0.0001

Data Index: 1341138 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.7728. Min Act: -0.0001

Data Index: 1210678 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6941. Min Act: -0.0001

Data Index: 1480016 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6646. Min Act: -0.0001

Data Index: 555724 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6513. Min Act: -0.0001

Data Index: 381945 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6564. Min Act: -0.0001

Data Index: 189282 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6259. Min Act: -0.0001

Data Index: 547918 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5768. Min Act: -0.0001

Data Index: 833116 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5689. Min Act: -0.0001

Data Index: 1180894 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5843. Min Act: -0.0001

Data Index: 609989 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6354. Min Act: -0.0001

Data Index: 304153 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5952. Min Act: -0.0001

Data Index: 495732 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5880. Min Act: -0.0001

Data Index: 287257 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5875. Min Act: -0.0001

Data Index: 866912 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5661. Min Act: -0.0001

Data Index: 1083951 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5759. Min Act: -0.0001

Data Index: 1231271 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5944. Min Act: -0.0001

Data Index: 732870 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.6180. Min Act: -0.0001

Data Index: 747848 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5729. Min Act: -0.0001

Data Index: 1412054 (Python Code)

Max Activating Token Index: 878

Text #19

Max Range: 0.8507. Min Range: -0.8507

Max Act: 0.5533. Min Act: -0.0001

Data Index: 745294 (C4 (Web Text))

Max Activating Token Index: 720