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

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

Neuron 4041 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.7184. Min Act: -0.0000

Data Index: 198677 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.7494. Min Act: -0.0000

Data Index: 561913 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.6479. Min Act: -0.0000

Data Index: 727747 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1287078 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.6199. Min Act: -0.0000

Data Index: 817811 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5682. Min Act: -0.0000

Data Index: 23826 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5650. Min Act: -0.0000

Data Index: 814809 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5920. Min Act: -0.0000

Data Index: 650039 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5503. Min Act: -0.0000

Data Index: 422911 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.4909. Min Act: -0.0000

Data Index: 800180 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1140036 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5660. Min Act: -0.0000

Data Index: 181789 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1245428 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1301738 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5297. Min Act: -0.0000

Data Index: 681927 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5264. Min Act: -0.0001

Data Index: 325574 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.4899. Min Act: -0.0001

Data Index: 1354497 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1059434 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1199964 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.7494. Min Range: -0.7494

Max Act: 0.5636. Min Act: -0.0000

Data Index: 880506 (C4 (Web Text))

Max Activating Token Index: 651