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

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

Neuron 2258 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: 3.8699. Min Range: -3.8699

Max Act: 3.8699. Min Act: -0.0000

Data Index: 1187504 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 3.8699. Min Range: -3.8699

Max Act: 3.7718. Min Act: -0.0000

Data Index: 328026 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 3.8699. Min Range: -3.8699

Max Act: 3.3772. Min Act: -0.0000

Data Index: 910496 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 3.8699. Min Range: -3.8699

Max Act: 3.3285. Min Act: -0.0000

Data Index: 433216 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 3.8699. Min Range: -3.8699

Max Act: 3.2065. Min Act: -0.0000

Data Index: 504588 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 3.8699. Min Range: -3.8699

Max Act: 3.3543. Min Act: -0.0000

Data Index: 14838 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 3.8699. Min Range: -3.8699

Max Act: 3.1382. Min Act: -0.0000

Data Index: 797734 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.9723. Min Act: -0.0000

Data Index: 1244816 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.9376. Min Act: -0.0000

Data Index: 565753 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.8933. Min Act: -0.0000

Data Index: 565100 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.8679. Min Act: -0.0000

Data Index: 175301 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.7815. Min Act: -0.0000

Data Index: 712761 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.8762. Min Act: -0.0000

Data Index: 145199 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.7358. Min Act: -0.0000

Data Index: 591922 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.8531. Min Act: -0.0000

Data Index: 697246 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.8481. Min Act: -0.0000

Data Index: 766037 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.7032. Min Act: -0.0000

Data Index: 341957 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.7841. Min Act: -0.0000

Data Index: 1165906 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.7668. Min Act: -0.0000

Data Index: 1155728 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 3.8699. Min Range: -3.8699

Max Act: 2.7642. Min Act: -0.0000

Data Index: 663476 (C4 (Web Text))

Max Activating Token Index: 30