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

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

Neuron 530 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.7348. Min Act: -0.0000

Data Index: 239658 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.6129. Min Act: -0.0000

Data Index: 218469 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.8873. Min Act: -0.0000

Data Index: 26007 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.5564. Min Act: -0.0000

Data Index: 1089773 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.5438. Min Act: -0.0000

Data Index: 658877 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.1769. Min Act: -0.0000

Data Index: 936875 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0618. Min Act: -0.0000

Data Index: 789100 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.2644. Min Act: -0.0000

Data Index: 928903 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.1720. Min Act: -0.0000

Data Index: 331025 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.3375. Min Act: -0.0000

Data Index: 336283 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0827. Min Act: -0.0000

Data Index: 169294 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.2186. Min Act: -0.0000

Data Index: 622010 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0687. Min Act: -0.0000

Data Index: 844255 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0178. Min Act: -0.0000

Data Index: 100249 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.1124. Min Act: -0.0000

Data Index: 1093232 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0918. Min Act: -0.0000

Data Index: 1108893 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0849. Min Act: -0.0000

Data Index: 167927 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0908. Min Act: -0.0000

Data Index: 326984 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 2.8873. Min Range: -2.8873

Max Act: 1.9334. Min Act: -0.0000

Data Index: 563691 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0090. Min Act: -0.0000

Data Index: 1118615 (C4 (Web Text))

Max Activating Token Index: 57