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

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

Neuron 4446 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: 0.1390. Min Range: -0.1390

Max Act: 0.1390. Min Act: -0.0000

Data Index: 611061 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1317. Min Act: -0.0000

Data Index: 452209 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1229. Min Act: -0.0000

Data Index: 763004 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1452796 (Python Code)

Max Activating Token Index: 347

Text #4

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1053. Min Act: -0.0000

Data Index: 649264 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1066. Min Act: -0.0000

Data Index: 278009 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1073114 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1000264 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0973. Min Act: -0.0000

Data Index: 53079 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1195354 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1295481 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0991. Min Act: -0.0000

Data Index: 856554 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0988. Min Act: -0.0000

Data Index: 329147 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1083261 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0966. Min Act: -0.0000

Data Index: 118187 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0926. Min Act: -0.0000

Data Index: 955779 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0958. Min Act: -0.0000

Data Index: 210200 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0957. Min Act: -0.0000

Data Index: 800622 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1186271 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.0905. Min Act: -0.0000

Data Index: 610930 (C4 (Web Text))

Max Activating Token Index: 83