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

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

Neuron 1053 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: 0.1879. Min Range: -0.1879

Max Act: 0.1879. Min Act: -0.0000

Data Index: 530829 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1532. Min Act: -0.0000

Data Index: 192663 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1195. Min Act: -0.0000

Data Index: 489472 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1232. Min Act: -0.0000

Data Index: 40865 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1178. Min Act: -0.0000

Data Index: 429321 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1094. Min Act: -0.0000

Data Index: 525989 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1263. Min Act: -0.0000

Data Index: 784321 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1216805 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1004. Min Act: -0.0000

Data Index: 799389 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1032818 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.0953. Min Act: -0.0000

Data Index: 700664 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1056. Min Act: -0.0000

Data Index: 659504 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.0977. Min Act: -0.0000

Data Index: 643060 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1006. Min Act: -0.0000

Data Index: 607552 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.0934. Min Act: -0.0000

Data Index: 64185 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.0923. Min Act: -0.0000

Data Index: 821431 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.0955. Min Act: -0.0000

Data Index: 718488 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.0897. Min Act: -0.0000

Data Index: 982100 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1176039 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.0848. Min Act: -0.0000

Data Index: 221947 (C4 (Web Text))

Max Activating Token Index: 352