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

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

Neuron 3496 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: 3.0546. Min Range: -3.0546

Max Act: 2.6382. Min Act: -0.0000

Data Index: 447124 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 3.0546. Min Range: -3.0546

Max Act: 3.0546. Min Act: -0.0000

Data Index: 1014074 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.9032. Min Act: -0.0000

Data Index: 1041436 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.6273. Min Act: -0.0000

Data Index: 1323662 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.7598. Min Act: -0.0000

Data Index: 1359655 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.5266. Min Act: -0.0000

Data Index: 1144680 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.5487. Min Act: -0.0000

Data Index: 48849 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.5450. Min Act: -0.0000

Data Index: 1016058 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.5329. Min Act: -0.0000

Data Index: 729233 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.5065. Min Act: -0.0000

Data Index: 80903 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.5823. Min Act: -0.0000

Data Index: 634860 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.3754. Min Act: -0.0000

Data Index: 581145 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.3770. Min Act: -0.0000

Data Index: 441033 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.4510. Min Act: -0.0000

Data Index: 759778 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 3.0546. Min Range: -3.0546

Max Act: 1.8142. Min Act: -0.0000

Data Index: 81996 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.3254. Min Act: -0.0000

Data Index: 850689 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.1834. Min Act: -0.0000

Data Index: 411905 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 3.0546. Min Range: -3.0546

Max Act: 1.9436. Min Act: -0.0000

Data Index: 45429 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.2775. Min Act: -0.0000

Data Index: 1290983 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 3.0546. Min Range: -3.0546

Max Act: 2.2576. Min Act: -0.0000

Data Index: 492895 (C4 (Web Text))

Max Activating Token Index: 399