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

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

Neuron 3627 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.5368. Min Act: -0.0000

Data Index: 492776 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.5258. Min Act: -0.0000

Data Index: 643589 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4890. Min Act: -0.0000

Data Index: 859106 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4793. Min Act: -0.0000

Data Index: 752015 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1191850 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1342852 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4898. Min Act: -0.0000

Data Index: 329093 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1120417 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4532. Min Act: -0.0000

Data Index: 761463 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1308734 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4743. Min Act: -0.0000

Data Index: 134852 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4391. Min Act: -0.0000

Data Index: 207968 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4153. Min Act: -0.0000

Data Index: 134331 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4352. Min Act: -0.0000

Data Index: 440402 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4233. Min Act: -0.0000

Data Index: 639811 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1052537 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4118. Min Act: -0.0000

Data Index: 403885 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4017. Min Act: -0.0000

Data Index: 591893 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.3986. Min Act: -0.0000

Data Index: 62617 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.5368. Min Range: -0.5368

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1194334 (C4 (Web Text))

Max Activating Token Index: 220