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

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

Neuron 191 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4842. Min Range: -6.4842

Max Act: 6.4842. Min Act: -0.0000

Data Index: 984807 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 6.4842. Min Range: -6.4842

Max Act: 6.2747. Min Act: -0.0000

Data Index: 308034 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 6.4842. Min Range: -6.4842

Max Act: 6.1973. Min Act: -0.0000

Data Index: 1111095 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.9122. Min Act: -0.0000

Data Index: 321580 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.9565. Min Act: -0.0000

Data Index: 774955 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.6178. Min Act: -0.0000

Data Index: 1308384 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.8096. Min Act: -0.0000

Data Index: 909720 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.5373. Min Act: -0.0000

Data Index: 977249 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.5157. Min Act: -0.0000

Data Index: 474619 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.3053. Min Act: -0.0000

Data Index: 310099 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.2969. Min Act: -0.0000

Data Index: 1043338 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.0509. Min Act: -0.0000

Data Index: 213225 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.3908. Min Act: -0.0000

Data Index: 142546 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.5560. Min Act: -0.0000

Data Index: 204591 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.3470. Min Act: -0.0000

Data Index: 357655 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 6.4842. Min Range: -6.4842

Max Act: 4.9451. Min Act: -0.0000

Data Index: 353937 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.1559. Min Act: -0.0000

Data Index: 660468 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.3180. Min Act: -0.0000

Data Index: 655370 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.3030. Min Act: -0.0000

Data Index: 64509 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 6.4842. Min Range: -6.4842

Max Act: 5.1123. Min Act: -0.0000

Data Index: 661999 (C4 (Web Text))

Max Activating Token Index: 276