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

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

Neuron 1416 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: 0.8764. Min Range: -0.8764

Max Act: 0.8764. Min Act: 0.0000

Data Index: 1059339 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.8075. Min Act: -0.0000

Data Index: 660870 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7399. Min Act: -0.0000

Data Index: 422434 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6718. Min Act: -0.0000

Data Index: 121695 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6689. Min Act: -0.0000

Data Index: 302762 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6391. Min Act: -0.0000

Data Index: 644206 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6654. Min Act: -0.0000

Data Index: 976529 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1123128 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6209. Min Act: -0.0000

Data Index: 801800 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6179. Min Act: 0.0000

Data Index: 1043677 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6308. Min Act: -0.0000

Data Index: 149810 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5936. Min Act: -0.0000

Data Index: 596905 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6088. Min Act: -0.0000

Data Index: 610940 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6028. Min Act: -0.0000

Data Index: 212734 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1150513 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5655. Min Act: -0.0000

Data Index: 56567 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6216. Min Act: -0.0000

Data Index: 117371 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5962. Min Act: -0.0000

Data Index: 943493 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5566. Min Act: -0.0000

Data Index: 462737 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1192624 (C4 (Web Text))

Max Activating Token Index: 509