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

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

Neuron 0 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: 2.1141. Min Range: -2.1141

Max Act: 2.1141. Min Act: -0.0000

Data Index: 87252 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.9954. Min Act: -0.0000

Data Index: 1293990 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.9585. Min Act: -0.0000

Data Index: 999070 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 2.1141. Min Range: -2.1141

Max Act: 2.0507. Min Act: -0.0000

Data Index: 59806 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.9096. Min Act: 0.0000

Data Index: 1146541 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.9064. Min Act: -0.0000

Data Index: 1357787 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.8465. Min Act: -0.0000

Data Index: 1270961 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.9208. Min Act: -0.0000

Data Index: 760214 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.7597. Min Act: -0.0000

Data Index: 670317 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.8118. Min Act: -0.0000

Data Index: 763991 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.7720. Min Act: -0.0000

Data Index: 521498 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.6423. Min Act: -0.0000

Data Index: 973559 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.6320. Min Act: -0.0000

Data Index: 176554 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.5988. Min Act: -0.0000

Data Index: 654972 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.6606. Min Act: -0.0000

Data Index: 170197 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.5323. Min Act: 0.0001

Data Index: 980484 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.5816. Min Act: -0.0000

Data Index: 387990 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.4947. Min Act: -0.0000

Data Index: 56462 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.4551. Min Act: -0.0000

Data Index: 1096765 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 2.1141. Min Range: -2.1141

Max Act: 1.3497. Min Act: -0.0000

Data Index: 505161 (C4 (Web Text))

Max Activating Token Index: 453