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

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

Neuron 3220 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0650. Min Range: -1.0650

Max Act: 1.0650. Min Act: -0.0000

Data Index: 426033 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9288. Min Act: -0.0000

Data Index: 900158 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9178. Min Act: -0.0000

Data Index: 568191 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9399. Min Act: -0.0000

Data Index: 400552 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9115. Min Act: -0.0000

Data Index: 339819 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8927. Min Act: -0.0000

Data Index: 194357 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8896. Min Act: -0.0000

Data Index: 549225 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8982. Min Act: -0.0000

Data Index: 339179 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8676. Min Act: -0.0000

Data Index: 685563 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1218738 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8488. Min Act: -0.0000

Data Index: 749325 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8603. Min Act: -0.0000

Data Index: 999943 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7722. Min Act: -0.0000

Data Index: 119474 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7609. Min Act: -0.0000

Data Index: 268098 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7630. Min Act: -0.0000

Data Index: 860814 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7544. Min Act: -0.0000

Data Index: 827809 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7215. Min Act: -0.0000

Data Index: 320304 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1139750 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7451. Min Act: -0.0000

Data Index: 301540 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.7361. Min Act: -0.0000

Data Index: 197287 (C4 (Web Text))

Max Activating Token Index: 850