Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1467 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3255. Min Range: -1.3255

Max Act: 1.3255. Min Act: -0.0001

Data Index: 763924 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 1.3255. Min Range: -1.3255

Max Act: 1.1650. Min Act: -0.0001

Data Index: 675504 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9836. Min Act: -0.0001

Data Index: 542524 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9733. Min Act: -0.0001

Data Index: 888366 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 1.3255. Min Range: -1.3255

Max Act: 1.0033. Min Act: -0.0001

Data Index: 148146 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 1.3255. Min Range: -1.3255

Max Act: 1.0057. Min Act: -0.0001

Data Index: 939185 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9057. Min Act: -0.0001

Data Index: 890784 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1022733 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9237. Min Act: -0.0001

Data Index: 1321964 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9338. Min Act: -0.0001

Data Index: 309324 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8802. Min Act: -0.0001

Data Index: 761069 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9485. Min Act: -0.0001

Data Index: 1150236 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9200. Min Act: -0.0001

Data Index: 469178 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9058. Min Act: -0.0001

Data Index: 30781 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8947. Min Act: -0.0001

Data Index: 556914 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9156. Min Act: -0.0001

Data Index: 439241 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8812. Min Act: -0.0001

Data Index: 1115114 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8788. Min Act: -0.0001

Data Index: 1103502 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8993. Min Act: -0.0001

Data Index: 342902 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8585. Min Act: -0.0001

Data Index: 964730 (C4 (Web Text))

Max Activating Token Index: 405