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

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

Neuron 4459 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4559. Min Range: -2.4559

Max Act: 2.4559. Min Act: -0.0000

Data Index: 497919 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.7893. Min Act: -0.0000

Data Index: 1148825 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.5215. Min Act: -0.0000

Data Index: 951863 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.4244. Min Act: -0.0000

Data Index: 248703 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.4576. Min Act: -0.0000

Data Index: 150621 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.3975. Min Act: -0.0000

Data Index: 253328 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1291260 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.3492. Min Act: -0.0000

Data Index: 1171979 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.3335. Min Act: -0.0000

Data Index: 140916 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.3429. Min Act: -0.0000

Data Index: 439131 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.3195. Min Act: -0.0000

Data Index: 922156 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.2233. Min Act: -0.0000

Data Index: 26480 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1144370 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.2498. Min Act: -0.0000

Data Index: 786403 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.1738. Min Act: -0.0000

Data Index: 318854 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.1596. Min Act: -0.0000

Data Index: 71237 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.2374. Min Act: -0.0000

Data Index: 579800 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.2183. Min Act: -0.0000

Data Index: 895564 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.2121. Min Act: -0.0000

Data Index: 179382 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 2.4559. Min Range: -2.4559

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1049730 (C4 (Web Text))

Max Activating Token Index: 610