Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4235 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2235. Min Range: -2.2235

Max Act: 2.2235. Min Act: -0.0000

Data Index: 656539 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.9627. Min Act: -0.0000

Data Index: 269330 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.7378. Min Act: -0.0000

Data Index: 496812 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.8494. Min Act: -0.0000

Data Index: 1017366 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.8175. Min Act: -0.0000

Data Index: 83350 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.8542. Min Act: 0.0000

Data Index: 490380 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.7800. Min Act: -0.0000

Data Index: 677494 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6471. Min Act: -0.0000

Data Index: 519892 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6325. Min Act: 0.0000

Data Index: 821066 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.4604. Min Act: 0.0000

Data Index: 836856 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6122. Min Act: 0.0001

Data Index: 365684 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1207045 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.4261. Min Act: -0.0000

Data Index: 1036121 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.4867. Min Act: -0.0000

Data Index: 992853 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.5207. Min Act: -0.0000

Data Index: 1229937 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.4882. Min Act: -0.0000

Data Index: 985019 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.4484. Min Act: -0.0000

Data Index: 317218 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.3640. Min Act: -0.0000

Data Index: 408520 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.2600. Min Act: -0.0000

Data Index: 855462 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.3017. Min Act: 0.0000

Data Index: 923846 (C4 (Web Text))

Max Activating Token Index: 34