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

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

Neuron 1121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1309709 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1294347 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8706. Min Act: -0.0000

Data Index: 689963 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7852. Min Act: -0.0000

Data Index: 750328 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7673. Min Act: -0.0000

Data Index: 192348 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7622. Min Act: -0.0000

Data Index: 689719 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8906. Min Act: -0.0000

Data Index: 868106 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8486. Min Act: -0.0000

Data Index: 596502 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8913. Min Act: -0.0000

Data Index: 411550 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7623. Min Act: -0.0000

Data Index: 405034 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7164. Min Act: -0.0000

Data Index: 375455 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7512. Min Act: -0.0000

Data Index: 833789 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1080923 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7436. Min Act: -0.0000

Data Index: 72891 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7088. Min Act: -0.0000

Data Index: 885849 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7252. Min Act: -0.0000

Data Index: 832998 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1116277 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7155. Min Act: -0.0000

Data Index: 126799 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7231. Min Act: -0.0000

Data Index: 885935 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.6728. Min Act: -0.0000

Data Index: 895401 (C4 (Web Text))

Max Activating Token Index: 325