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

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

Neuron 5757 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: 1.4109. Min Range: -1.4109

Max Act: 1.4109. Min Act: -0.0000

Data Index: 293987 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9163. Min Act: -0.0000

Data Index: 985884 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8378. Min Act: -0.0000

Data Index: 221788 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.7190. Min Act: -0.0000

Data Index: 867099 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.7035. Min Act: -0.0000

Data Index: 479612 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.7121. Min Act: -0.0000

Data Index: 255073 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.6691. Min Act: -0.0000

Data Index: 422630 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.6441. Min Act: -0.0000

Data Index: 517968 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.6567. Min Act: -0.0000

Data Index: 887202 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1164882 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.5655. Min Act: -0.0000

Data Index: 381195 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.6671. Min Act: -0.0000

Data Index: 17344 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.5401. Min Act: -0.0000

Data Index: 812483 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.6378. Min Act: -0.0000

Data Index: 437108 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.5934. Min Act: -0.0000

Data Index: 759677 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.5764. Min Act: -0.0000

Data Index: 828583 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.6045. Min Act: -0.0000

Data Index: 722958 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.6161. Min Act: -0.0000

Data Index: 168052 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.5851. Min Act: -0.0000

Data Index: 107372 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.5631. Min Act: -0.0000

Data Index: 84335 (C4 (Web Text))

Max Activating Token Index: 219