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

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

Neuron 3654 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: 2.1127. Min Range: -2.1127

Max Act: 2.1127. Min Act: -0.0000

Data Index: 876390 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.4832. Min Act: -0.0000

Data Index: 871566 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1205212 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.4326. Min Act: -0.0000

Data Index: 1275433 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.3704. Min Act: -0.0000

Data Index: 735902 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1267216 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.3374. Min Act: -0.0000

Data Index: 570581 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.2486. Min Act: -0.0000

Data Index: 337422 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.2743. Min Act: -0.0000

Data Index: 914014 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1025651 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.2447. Min Act: -0.0000

Data Index: 937796 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.1865. Min Act: -0.0000

Data Index: 456152 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.0656. Min Act: -0.0000

Data Index: 287681 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1346435 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.2255. Min Act: -0.0000

Data Index: 758710 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.1700. Min Act: -0.0000

Data Index: 599562 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.2432. Min Act: -0.0000

Data Index: 940532 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.1134. Min Act: -0.0000

Data Index: 536009 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 2.1127. Min Range: -2.1127

Max Act: 0.9746. Min Act: -0.0000

Data Index: 135801 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 2.1127. Min Range: -2.1127

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1296604 (C4 (Web Text))

Max Activating Token Index: 810