Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1491 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1355089 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6901. Min Act: 0.0001

Data Index: 1314732 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.7006. Min Act: 0.0001

Data Index: 270228 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6804. Min Act: 0.0000

Data Index: 340783 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1211237 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6682. Min Act: 0.0000

Data Index: 1181256 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6168. Min Act: -0.0000

Data Index: 940395 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6342. Min Act: 0.0000

Data Index: 341450 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6770. Min Act: 0.0001

Data Index: 169721 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6143. Min Act: 0.0001

Data Index: 118121 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1305559 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5896. Min Act: -0.0000

Data Index: 395226 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5450. Min Act: -0.0000

Data Index: 820650 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5657. Min Act: -0.0000

Data Index: 141301 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5531. Min Act: -0.0000

Data Index: 868623 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5506. Min Act: -0.0000

Data Index: 177961 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5169. Min Act: -0.0000

Data Index: 783222 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5307. Min Act: -0.0000

Data Index: 111703 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.5266. Min Act: 0.0001

Data Index: 572531 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.4997. Min Act: 0.0001

Data Index: 718143 (C4 (Web Text))

Max Activating Token Index: 725