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

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

Neuron 5704 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1226. Min Range: -2.1226

Max Act: 2.1226. Min Act: -0.0000

Data Index: 1263880 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 2.1226. Min Range: -2.1226

Max Act: 2.0159. Min Act: -0.0000

Data Index: 729231 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.9887. Min Act: -0.0000

Data Index: 256816 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 2.1226. Min Range: -2.1226

Max Act: 2.0513. Min Act: -0.0000

Data Index: 1104607 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 2.1226. Min Range: -2.1226

Max Act: 2.0019. Min Act: -0.0000

Data Index: 762817 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 2.1226. Min Range: -2.1226

Max Act: 2.0087. Min Act: -0.0000

Data Index: 1347554 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.8713. Min Act: -0.0000

Data Index: 1280046 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.9549. Min Act: -0.0000

Data Index: 1211406 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.8319. Min Act: -0.0000

Data Index: 151603 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.8824. Min Act: -0.0000

Data Index: 926483 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.9028. Min Act: -0.0000

Data Index: 434541 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.9028. Min Act: -0.0000

Data Index: 603195 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.9049. Min Act: -0.0000

Data Index: 206430 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.8003. Min Act: -0.0000

Data Index: 504360 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.8987. Min Act: -0.0000

Data Index: 699046 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.7807. Min Act: -0.0000

Data Index: 859185 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.7716. Min Act: -0.0000

Data Index: 1200487 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.8540. Min Act: -0.0000

Data Index: 1290309 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.8523. Min Act: -0.0000

Data Index: 98038 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 2.1226. Min Range: -2.1226

Max Act: 1.9507. Min Act: -0.0000

Data Index: 844855 (C4 (Web Text))

Max Activating Token Index: 923