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

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

Neuron 3953 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: 2.6725. Min Range: -2.6725

Max Act: 2.6725. Min Act: -0.0000

Data Index: 20834 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 2.6725. Min Range: -2.6725

Max Act: 2.4329. Min Act: -0.0000

Data Index: 591338 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.8954. Min Act: -0.0000

Data Index: 429526 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.9444. Min Act: -0.0000

Data Index: 764563 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.8220. Min Act: -0.0000

Data Index: 606139 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.9069. Min Act: -0.0000

Data Index: 297739 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1286543 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.7780. Min Act: -0.0000

Data Index: 11570 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.5759. Min Act: -0.0000

Data Index: 929533 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.5674. Min Act: -0.0000

Data Index: 298220 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.7579. Min Act: -0.0000

Data Index: 730766 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.7640. Min Act: -0.0000

Data Index: 3442 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.6482. Min Act: -0.0000

Data Index: 944058 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.6436. Min Act: -0.0000

Data Index: 1296392 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.7415. Min Act: -0.0000

Data Index: 1064274 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.5999. Min Act: -0.0000

Data Index: 751823 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.6804. Min Act: -0.0000

Data Index: 49550 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.6957. Min Act: -0.0000

Data Index: 201619 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.5997. Min Act: -0.0000

Data Index: 759717 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 2.6725. Min Range: -2.6725

Max Act: 1.6857. Min Act: -0.0000

Data Index: 747309 (C4 (Web Text))

Max Activating Token Index: 56