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

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

Neuron 4812 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1252414 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1037. Min Act: -0.0002

Data Index: 304839 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1201830 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1319905 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1505305 (Python Code)

Max Activating Token Index: 931

Text #5

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0901. Min Act: -0.0002

Data Index: 684466 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0927. Min Act: -0.0002

Data Index: 840623 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0879. Min Act: -0.0002

Data Index: 94381 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0895. Min Act: -0.0002

Data Index: 61441 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0831. Min Act: -0.0002

Data Index: 563582 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0851. Min Act: -0.0002

Data Index: 311541 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1516137 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1152286 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0818. Min Act: -0.0002

Data Index: 18370 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0894. Min Act: -0.0002

Data Index: 250642 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0807. Min Act: -0.0002

Data Index: 326177 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1160421 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0826. Min Act: -0.0002

Data Index: 700939 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0859. Min Act: -0.0002

Data Index: 172425 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0789. Min Act: -0.0002

Data Index: 232821 (C4 (Web Text))

Max Activating Token Index: 228