Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1749 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.7461. Min Act: -0.0001

Data Index: 617791 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.4834. Min Act: -0.0001

Data Index: 444845 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.4789. Min Act: -0.0001

Data Index: 832790 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.4000. Min Act: -0.0001

Data Index: 945154 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.5187. Min Act: -0.0001

Data Index: 1153558 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.3667. Min Act: -0.0001

Data Index: 1304744 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.2651. Min Act: -0.0001

Data Index: 984323 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.3239. Min Act: -0.0001

Data Index: 882016 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.3142. Min Act: -0.0001

Data Index: 991651 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.3875. Min Act: -0.0001

Data Index: 362933 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.3436. Min Act: -0.0001

Data Index: 656777 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.1710. Min Act: -0.0001

Data Index: 270337 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.2523. Min Act: -0.0001

Data Index: 677134 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.2007. Min Act: -0.0001

Data Index: 1251021 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.3416. Min Act: -0.0001

Data Index: 447003 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.3354. Min Act: -0.0001

Data Index: 252762 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.2905. Min Act: -0.0001

Data Index: 1116335 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.1819. Min Act: -0.0001

Data Index: 558101 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.3205. Min Act: -0.0001

Data Index: 1199141 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 1.7461. Min Range: -1.7461

Max Act: 1.2856. Min Act: -0.0001

Data Index: 1011624 (C4 (Web Text))

Max Activating Token Index: 37