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

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

Neuron 5099 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.8038. Min Act: -0.0000

Data Index: 580681 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.4237. Min Act: -0.0000

Data Index: 93647 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1267743 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.6191. Min Act: -0.0000

Data Index: 473668 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.4800. Min Act: -0.0000

Data Index: 788559 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.3613. Min Act: -0.0000

Data Index: 979895 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1059229 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.4501. Min Act: -0.0000

Data Index: 780788 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.3630. Min Act: -0.0000

Data Index: 856701 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1053259 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.2007. Min Act: -0.0000

Data Index: 455802 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.2329. Min Act: -0.0000

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.2946. Min Act: -0.0000

Data Index: 1012194 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.2832. Min Act: -0.0000

Data Index: 848529 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.2690. Min Act: -0.0000

Data Index: 743229 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.2584. Min Act: -0.0000

Data Index: 795210 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.2463. Min Act: -0.0000

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.1421. Min Act: -0.0000

Data Index: 922490 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.1632. Min Act: -0.0000

Data Index: 844932 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 1.8038. Min Range: -1.8038

Max Act: 1.3689. Min Act: -0.0000

Data Index: 451614 (C4 (Web Text))

Max Activating Token Index: 849