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

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

Neuron 610 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3398. Min Range: -1.3398

Max Act: 1.3398. Min Act: -0.0000

Data Index: 316240 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.3398. Min Range: -1.3398

Max Act: 1.0126. Min Act: -0.0000

Data Index: 792538 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.9742. Min Act: -0.0000

Data Index: 350713 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.9123. Min Act: -0.0000

Data Index: 193565 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.8516. Min Act: -0.0000

Data Index: 685533 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.8685. Min Act: -0.0000

Data Index: 532145 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1298850 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1035109 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1051518 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.8196. Min Act: -0.0000

Data Index: 224062 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.7607. Min Act: -0.0000

Data Index: 728348 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.6993. Min Act: -0.0000

Data Index: 226100 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.8192. Min Act: -0.0000

Data Index: 304628 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1027040 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.6969. Min Act: -0.0000

Data Index: 923603 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1296655 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1266919 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.6384. Min Act: -0.0000

Data Index: 333819 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.6828. Min Act: -0.0000

Data Index: 512973 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 1.3398. Min Range: -1.3398

Max Act: 0.6331. Min Act: -0.0000

Data Index: 330197 (C4 (Web Text))

Max Activating Token Index: 744