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

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

Neuron 3670 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9939. Min Act: -0.0000

Data Index: 186782 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.7552. Min Act: -0.0000

Data Index: 1189432 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9364. Min Act: -0.0000

Data Index: 618914 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.8203. Min Act: -0.0000

Data Index: 668828 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.9075. Min Act: -0.0000

Data Index: 1120927 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.8887. Min Act: -0.0000

Data Index: 1319395 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.8627. Min Act: -0.0000

Data Index: 426820 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.7459. Min Act: -0.0000

Data Index: 543376 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.7105. Min Act: -0.0000

Data Index: 151075 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.7822. Min Act: -0.0000

Data Index: 600217 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.6630. Min Act: -0.0000

Data Index: 278504 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.7403. Min Act: -0.0000

Data Index: 474689 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.7481. Min Act: -0.0000

Data Index: 1092965 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.6414. Min Act: -0.0000

Data Index: 1187648 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.7256. Min Act: -0.0000

Data Index: 192590 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1218962 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.5345. Min Act: -0.0000

Data Index: 1079011 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.6939. Min Act: -0.0000

Data Index: 386499 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.7008. Min Act: -0.0000

Data Index: 481384 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 1.9939. Min Range: -1.9939

Max Act: 1.6823. Min Act: -0.0000

Data Index: 927059 (C4 (Web Text))

Max Activating Token Index: 137