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

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

Neuron 3237 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: 5.7216. Min Range: -5.7216

Max Act: 5.5883. Min Act: -0.0000

Data Index: 1032171 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 5.7216. Min Range: -5.7216

Max Act: 5.7216. Min Act: -0.0000

Data Index: 1309194 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 5.7216. Min Range: -5.7216

Max Act: 5.2348. Min Act: -0.0000

Data Index: 171291 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 5.7216. Min Range: -5.7216

Max Act: 5.3417. Min Act: -0.0000

Data Index: 1036258 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 5.7216. Min Range: -5.7216

Max Act: 5.1329. Min Act: -0.0000

Data Index: 1034970 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.9883. Min Act: -0.0000

Data Index: 525513 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 5.7216. Min Range: -5.7216

Max Act: 5.1638. Min Act: -0.0000

Data Index: 220769 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.7304. Min Act: -0.0000

Data Index: 1213864 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 5.7216. Min Range: -5.7216

Max Act: 5.2131. Min Act: -0.0000

Data Index: 7536 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 5.7216. Min Range: -5.7216

Max Act: 5.1760. Min Act: -0.0000

Data Index: 314725 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 5.7216. Min Range: -5.7216

Max Act: 5.2158. Min Act: -0.0000

Data Index: 773382 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 5.7216. Min Range: -5.7216

Max Act: 5.1659. Min Act: -0.0000

Data Index: 797332 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.8281. Min Act: -0.0000

Data Index: 626105 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.7923. Min Act: -0.0000

Data Index: 1180413 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.7763. Min Act: -0.0000

Data Index: 1040478 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.7259. Min Act: -0.0000

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.3430. Min Act: -0.0000

Data Index: 546252 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.6819. Min Act: -0.0000

Data Index: 817644 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.6853. Min Act: -0.0000

Data Index: 901929 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 5.7216. Min Range: -5.7216

Max Act: 4.6750. Min Act: -0.0000

Data Index: 1256244 (C4 (Web Text))

Max Activating Token Index: 189