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

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

Neuron 2955 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: 1.3716. Min Range: -1.3716

Max Act: 1.3211. Min Act: -0.0001

Data Index: 556001 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3716. Min Act: -0.0001

Data Index: 1188246 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1826. Min Act: -0.0001

Data Index: 2069 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3167. Min Act: -0.0001

Data Index: 250670 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1639. Min Act: -0.0001

Data Index: 1122850 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1725. Min Act: -0.0001

Data Index: 1312431 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0725. Min Act: -0.0001

Data Index: 8156 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0941. Min Act: -0.0001

Data Index: 380779 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0594. Min Act: -0.0001

Data Index: 1037212 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1907. Min Act: -0.0001

Data Index: 202377 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1204. Min Act: -0.0001

Data Index: 1063200 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0550. Min Act: -0.0001

Data Index: 15576 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0168. Min Act: -0.0001

Data Index: 1057775 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1686. Min Act: -0.0001

Data Index: 1242597 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0095. Min Act: -0.0001

Data Index: 1244194 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0792. Min Act: -0.0001

Data Index: 595164 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0185. Min Act: -0.0001

Data Index: 366394 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0843. Min Act: -0.0001

Data Index: 749862 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0171. Min Act: -0.0001

Data Index: 742703 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9682. Min Act: -0.0001

Data Index: 1032981 (C4 (Web Text))

Max Activating Token Index: 668