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

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

Neuron 95 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0281. Min Range: -1.0281

Max Act: 1.0281. Min Act: -0.0000

Data Index: 961010 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1096923 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.9341. Min Act: -0.0000

Data Index: 172255 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8951. Min Act: -0.0000

Data Index: 795700 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1132351 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8961. Min Act: -0.0000

Data Index: 585658 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8135. Min Act: -0.0000

Data Index: 519054 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8387. Min Act: -0.0000

Data Index: 602203 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8157. Min Act: -0.0000

Data Index: 422171 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8612. Min Act: -0.0000

Data Index: 799001 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8777. Min Act: -0.0000

Data Index: 290773 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8505. Min Act: -0.0000

Data Index: 829654 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8222. Min Act: -0.0000

Data Index: 238028 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8222. Min Act: -0.0000

Data Index: 788373 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8379. Min Act: -0.0000

Data Index: 314951 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8107. Min Act: -0.0000

Data Index: 78884 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.7672. Min Act: -0.0000

Data Index: 777794 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.7782. Min Act: -0.0000

Data Index: 640166 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8014. Min Act: -0.0000

Data Index: 925627 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.0281. Min Range: -1.0281

Max Act: 0.8267. Min Act: -0.0000

Data Index: 959888 (C4 (Web Text))

Max Activating Token Index: 854