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

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

Neuron 2218 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.5427. Min Act: -0.0000

Data Index: 160645 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1278243 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.5075. Min Act: -0.0000

Data Index: 586265 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1219142 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1285215 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4777. Min Act: -0.0000

Data Index: 873017 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4423. Min Act: -0.0000

Data Index: 31052 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1227703 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1095064 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4391. Min Act: -0.0000

Data Index: 804687 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1038492 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4150. Min Act: -0.0000

Data Index: 491638 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4238. Min Act: -0.0000

Data Index: 986555 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4546. Min Act: -0.0000

Data Index: 653042 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4070. Min Act: -0.0000

Data Index: 950342 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4075. Min Act: -0.0000

Data Index: 385274 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.3962. Min Act: -0.0000

Data Index: 337482 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4032. Min Act: -0.0000

Data Index: 150538 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4114. Min Act: -0.0000

Data Index: 741459 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.5427. Min Range: -0.5427

Max Act: 0.4010. Min Act: -0.0000

Data Index: 616792 (C4 (Web Text))

Max Activating Token Index: 732