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

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

Neuron 2733 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.3230. Min Act: -0.0000

Data Index: 727934 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2945. Min Act: -0.0000

Data Index: 817999 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2873. Min Act: -0.0000

Data Index: 60430 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2564. Min Act: -0.0000

Data Index: 280234 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2500. Min Act: -0.0000

Data Index: 622840 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1109353 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2114. Min Act: -0.0000

Data Index: 806606 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1072040 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2217. Min Act: -0.0000

Data Index: 644 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2108. Min Act: -0.0000

Data Index: 684516 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2072. Min Act: -0.0000

Data Index: 329366 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2016. Min Act: -0.0000

Data Index: 316250 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1227508 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2060. Min Act: -0.0000

Data Index: 226903 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.1950. Min Act: -0.0000

Data Index: 685485 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.2015. Min Act: -0.0000

Data Index: 131329 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1356444 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.1848. Min Act: -0.0000

Data Index: 165066 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1159420 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.3230. Min Range: -0.3230

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1160371 (C4 (Web Text))

Max Activating Token Index: 394