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

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

Neuron 3336 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.7511. Min Act: -0.0001

Data Index: 120971 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.7134. Min Act: -0.0001

Data Index: 933482 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.8663. Min Act: -0.0001

Data Index: 1079914 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.2535. Min Act: -0.0001

Data Index: 461830 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.2439. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.1963. Min Act: -0.0001

Data Index: 124696 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.1273. Min Act: -0.0001

Data Index: 608776 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.1308. Min Act: -0.0001

Data Index: 630234 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.0672. Min Act: -0.0001

Data Index: 560574 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 1.8663. Min Range: -1.8663

Max Act: 0.9888. Min Act: -0.0001

Data Index: 525561 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.0676. Min Act: -0.0000

Data Index: 843315 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.0007. Min Act: -0.0001

Data Index: 1197355 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.0171. Min Act: -0.0001

Data Index: 184877 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.0097. Min Act: -0.0001

Data Index: 89724 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.8663. Min Range: -1.8663

Max Act: 0.9421. Min Act: -0.0001

Data Index: 46714 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.8663. Min Range: -1.8663

Max Act: 0.9425. Min Act: -0.0001

Data Index: 337110 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 1.8663. Min Range: -1.8663

Max Act: 0.9949. Min Act: -0.0001

Data Index: 162860 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 1.8663. Min Range: -1.8663

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1076020 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 1.8663. Min Range: -1.8663

Max Act: 0.8271. Min Act: -0.0001

Data Index: 43628 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 1.8663. Min Range: -1.8663

Max Act: 0.8944. Min Act: -0.0001

Data Index: 430458 (C4 (Web Text))

Max Activating Token Index: 760