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

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

Neuron 1444 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: 0.7820. Min Range: -0.7820

Max Act: 0.7820. Min Act: -0.0000

Data Index: 263557 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7584. Min Act: -0.0000

Data Index: 297831 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6612. Min Act: -0.0000

Data Index: 722643 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7707. Min Act: -0.0000

Data Index: 962417 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5890. Min Act: -0.0000

Data Index: 314370 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6172. Min Act: -0.0000

Data Index: 123581 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5706. Min Act: -0.0000

Data Index: 852280 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5986. Min Act: -0.0000

Data Index: 548080 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5915. Min Act: -0.0000

Data Index: 183282 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5787. Min Act: -0.0000

Data Index: 669876 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5566. Min Act: -0.0000

Data Index: 585320 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5620. Min Act: -0.0000

Data Index: 511750 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5609. Min Act: -0.0000

Data Index: 820048 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5405. Min Act: -0.0000

Data Index: 363190 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5386. Min Act: -0.0000

Data Index: 248759 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5294. Min Act: -0.0000

Data Index: 257347 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5743. Min Act: -0.0000

Data Index: 176715 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5014. Min Act: -0.0000

Data Index: 650738 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5442. Min Act: -0.0000

Data Index: 956093 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1239539 (C4 (Web Text))

Max Activating Token Index: 368