Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2743 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.9847. Min Act: -0.0000

Data Index: 949511 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.9928. Min Act: -0.0000

Data Index: 1117408 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.8586. Min Act: -0.0000

Data Index: 1156371 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.9587. Min Act: -0.0001

Data Index: 1331687 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.9457. Min Act: -0.0000

Data Index: 954453 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.8391. Min Act: -0.0001

Data Index: 4793 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.8879. Min Act: -0.0001

Data Index: 989587 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.8991. Min Act: -0.0000

Data Index: 725056 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.8449. Min Act: -0.0001

Data Index: 182664 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.7405. Min Act: -0.0000

Data Index: 509724 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.7752. Min Act: -0.0000

Data Index: 485535 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.8424. Min Act: -0.0000

Data Index: 669114 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.7399. Min Act: -0.0001

Data Index: 335291 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.8262. Min Act: -0.0001

Data Index: 366573 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.8277. Min Act: -0.0000

Data Index: 830462 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.9124. Min Act: -0.0000

Data Index: 960845 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.7560. Min Act: -0.0000

Data Index: 1282195 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1079463 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.8000. Min Act: -0.0000

Data Index: 188453 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.9928. Min Range: -1.9928

Max Act: 1.7904. Min Act: -0.0001

Data Index: 347105 (C4 (Web Text))

Max Activating Token Index: 695