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

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

Neuron 4635 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: 0.6382. Min Range: -0.6382

Max Act: 0.6382. Min Act: -0.0001

Data Index: 526456 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.6007. Min Act: -0.0001

Data Index: 1226763 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5811. Min Act: -0.0001

Data Index: 1069597 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5791. Min Act: -0.0001

Data Index: 1306792 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.6279. Min Act: -0.0001

Data Index: 181137 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5562. Min Act: -0.0001

Data Index: 1189016 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5988. Min Act: -0.0001

Data Index: 640834 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5556. Min Act: -0.0001

Data Index: 426252 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5046. Min Act: -0.0001

Data Index: 564931 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5803. Min Act: -0.0001

Data Index: 720171 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5636. Min Act: -0.0000

Data Index: 192131 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5285. Min Act: -0.0001

Data Index: 762021 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5295. Min Act: -0.0001

Data Index: 1203381 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5231. Min Act: -0.0001

Data Index: 841287 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4678. Min Act: -0.0001

Data Index: 707402 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5379. Min Act: -0.0001

Data Index: 1246713 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5189. Min Act: -0.0001

Data Index: 1226520 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.5003. Min Act: -0.0001

Data Index: 957185 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4945. Min Act: -0.0001

Data Index: 722707 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.6382. Min Range: -0.6382

Max Act: 0.4967. Min Act: -0.0001

Data Index: 948876 (C4 (Web Text))

Max Activating Token Index: 631