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

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

Neuron 3257 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5021. Min Range: -6.5021

Max Act: 6.5021. Min Act: -0.0000

Data Index: 1039123 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 6.5021. Min Range: -6.5021

Max Act: 6.1253. Min Act: -0.0000

Data Index: 818337 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 6.5021. Min Range: -6.5021

Max Act: 5.6396. Min Act: -0.0000

Data Index: 677789 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 6.5021. Min Range: -6.5021

Max Act: 5.4753. Min Act: -0.0000

Data Index: 217041 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 6.5021. Min Range: -6.5021

Max Act: 5.5421. Min Act: -0.0000

Data Index: 407212 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 6.5021. Min Range: -6.5021

Max Act: 5.3660. Min Act: -0.0000

Data Index: 1107390 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 6.5021. Min Range: -6.5021

Max Act: 5.2760. Min Act: -0.0000

Data Index: 82356 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 6.5021. Min Range: -6.5021

Max Act: 5.1390. Min Act: -0.0000

Data Index: 1042872 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 6.5021. Min Range: -6.5021

Max Act: 4.7307. Min Act: -0.0000

Data Index: 534667 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 6.5021. Min Range: -6.5021

Max Act: 4.9076. Min Act: -0.0000

Data Index: 579828 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 6.5021. Min Range: -6.5021

Max Act: 5.2491. Min Act: -0.0000

Data Index: 1147883 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 6.5021. Min Range: -6.5021

Max Act: 4.7263. Min Act: -0.0000

Data Index: 202768 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 6.5021. Min Range: -6.5021

Max Act: 4.7150. Min Act: -0.0000

Data Index: 486564 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 6.5021. Min Range: -6.5021

Max Act: 5.0177. Min Act: -0.0000

Data Index: 571705 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 6.5021. Min Range: -6.5021

Max Act: 5.0248. Min Act: -0.0000

Data Index: 575377 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 6.5021. Min Range: -6.5021

Max Act: 4.8064. Min Act: -0.0000

Data Index: 609562 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 6.5021. Min Range: -6.5021

Max Act: 4.9007. Min Act: -0.0000

Data Index: 264506 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 6.5021. Min Range: -6.5021

Max Act: 4.7395. Min Act: -0.0000

Data Index: 224321 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 6.5021. Min Range: -6.5021

Max Act: 4.6984. Min Act: -0.0000

Data Index: 63942 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 6.5021. Min Range: -6.5021

Max Act: 4.6388. Min Act: -0.0000

Data Index: 234423 (C4 (Web Text))

Max Activating Token Index: 778