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

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

Neuron 6143 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5312. Min Range: -6.5312

Max Act: 6.5312. Min Act: -0.0000

Data Index: 755594 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 6.5312. Min Range: -6.5312

Max Act: 6.2435. Min Act: -0.0000

Data Index: 814406 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 6.5312. Min Range: -6.5312

Max Act: 6.1566. Min Act: -0.0000

Data Index: 1125855 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 6.5312. Min Range: -6.5312

Max Act: 6.3324. Min Act: -0.0000

Data Index: 168441 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 6.5312. Min Range: -6.5312

Max Act: 6.1341. Min Act: -0.0000

Data Index: 1273019 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.6792. Min Act: -0.0000

Data Index: 1322662 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.7601. Min Act: -0.0000

Data Index: 776306 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.6717. Min Act: -0.0000

Data Index: 598289 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 6.5312. Min Range: -6.5312

Max Act: 6.2715. Min Act: -0.0000

Data Index: 409257 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.7407. Min Act: -0.0000

Data Index: 610116 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.6098. Min Act: -0.0000

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.5890. Min Act: -0.0000

Data Index: 837081 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.2859. Min Act: -0.0000

Data Index: 16061 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.2801. Min Act: -0.0000

Data Index: 902319 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 6.5312. Min Range: -6.5312

Max Act: 4.9027. Min Act: -0.0000

Data Index: 713156 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 6.5312. Min Range: -6.5312

Max Act: 4.9591. Min Act: -0.0000

Data Index: 859392 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 6.5312. Min Range: -6.5312

Max Act: 4.9491. Min Act: -0.0000

Data Index: 1006293 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 6.5312. Min Range: -6.5312

Max Act: 4.8937. Min Act: -0.0000

Data Index: 125396 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.0374. Min Act: -0.0000

Data Index: 1257441 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 6.5312. Min Range: -6.5312

Max Act: 5.1791. Min Act: -0.0000

Data Index: 1275293 (C4 (Web Text))

Max Activating Token Index: 960