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

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

Neuron 1991 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.9265. Min Act: -0.0000

Data Index: 328065 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.9152. Min Act: -0.0000

Data Index: 918568 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1258087 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.8028. Min Act: -0.0000

Data Index: 3917 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.7735. Min Act: -0.0000

Data Index: 481667 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.6737. Min Act: -0.0000

Data Index: 875716 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.4255. Min Act: -0.0000

Data Index: 623786 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1019681 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.4445. Min Act: -0.0000

Data Index: 465286 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1206280 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3942. Min Act: -0.0000

Data Index: 582431 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1341670 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3874. Min Act: -0.0000

Data Index: 13249 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1072233 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.4257. Min Act: -0.0000

Data Index: 72253 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3628. Min Act: -0.0000

Data Index: 738946 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3494. Min Act: -0.0000

Data Index: 441603 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3305. Min Act: -0.0000

Data Index: 365635 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3480. Min Act: -0.0000

Data Index: 116378 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.9265. Min Range: -0.9265

Max Act: 0.3728. Min Act: -0.0000

Data Index: 516496 (C4 (Web Text))

Max Activating Token Index: 998