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

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

Neuron 3550 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: 0.6389. Min Range: -0.6389

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1275809 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5432. Min Act: -0.0000

Data Index: 420478 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5469. Min Act: -0.0000

Data Index: 919497 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1247584 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4809. Min Act: -0.0000

Data Index: 116834 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1128250 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4849. Min Act: -0.0000

Data Index: 793064 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4804. Min Act: -0.0000

Data Index: 702950 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4654. Min Act: -0.0000

Data Index: 401036 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4799. Min Act: -0.0000

Data Index: 9425 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4726. Min Act: -0.0000

Data Index: 422053 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4451. Min Act: -0.0000

Data Index: 897211 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1084909 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1292885 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4485. Min Act: -0.0000

Data Index: 290541 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4513. Min Act: -0.0000

Data Index: 923826 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4472. Min Act: -0.0000

Data Index: 731817 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4330. Min Act: -0.0000

Data Index: 534872 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4286. Min Act: -0.0000

Data Index: 754215 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.6389. Min Range: -0.6389

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1148424 (C4 (Web Text))

Max Activating Token Index: 910