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

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

Neuron 3664 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4948. Min Range: -2.4948

Max Act: 2.4243. Min Act: -0.0000

Data Index: 741350 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 2.4948. Min Range: -2.4948

Max Act: 2.3025. Min Act: -0.0000

Data Index: 548718 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 2.4948. Min Range: -2.4948

Max Act: 2.4948. Min Act: -0.0000

Data Index: 740510 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.8087. Min Act: -0.0000

Data Index: 1187640 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.7778. Min Act: -0.0000

Data Index: 225908 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.5628. Min Act: -0.0000

Data Index: 872084 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.6570. Min Act: -0.0000

Data Index: 682475 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.8013. Min Act: -0.0000

Data Index: 1190852 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.7127. Min Act: -0.0000

Data Index: 865987 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.6053. Min Act: -0.0000

Data Index: 620 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.5104. Min Act: -0.0000

Data Index: 142339 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.6199. Min Act: -0.0000

Data Index: 1062214 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.5349. Min Act: -0.0000

Data Index: 438807 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1131168 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4229. Min Act: -0.0000

Data Index: 232837 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4921. Min Act: -0.0000

Data Index: 261774 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1263227 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4522. Min Act: -0.0000

Data Index: 1486485 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.5548. Min Act: -0.0000

Data Index: 540347 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.3551. Min Act: -0.0000

Data Index: 862824 (C4 (Web Text))

Max Activating Token Index: 693