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

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

Neuron 4318 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1688. Min Range: -6.1688

Max Act: 6.1688. Min Act: 0.0000

Data Index: 1277703 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 6.1688. Min Range: -6.1688

Max Act: 4.4630. Min Act: -0.0000

Data Index: 1051449 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 6.1688. Min Range: -6.1688

Max Act: 4.2724. Min Act: -0.0000

Data Index: 230812 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.9739. Min Act: -0.0000

Data Index: 727914 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.9840. Min Act: -0.0000

Data Index: 499337 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 6.1688. Min Range: -6.1688

Max Act: 4.1681. Min Act: -0.0000

Data Index: 411789 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.7225. Min Act: -0.0000

Data Index: 1240812 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.8845. Min Act: -0.0000

Data Index: 1229084 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.7529. Min Act: -0.0000

Data Index: 741250 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.6989. Min Act: -0.0000

Data Index: 707337 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.2936. Min Act: -0.0000

Data Index: 234226 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.2380. Min Act: -0.0000

Data Index: 500714 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.4158. Min Act: -0.0000

Data Index: 974407 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 6.1688. Min Range: -6.1688

Max Act: 3.0572. Min Act: -0.0000

Data Index: 998441 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 6.1688. Min Range: -6.1688

Max Act: 2.9330. Min Act: -0.0000

Data Index: 465060 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 6.1688. Min Range: -6.1688

Max Act: 2.8659. Min Act: -0.0000

Data Index: 137632 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 6.1688. Min Range: -6.1688

Max Act: 2.8352. Min Act: -0.0000

Data Index: 1201606 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 6.1688. Min Range: -6.1688

Max Act: 2.9687. Min Act: 0.0000

Data Index: 812823 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 6.1688. Min Range: -6.1688

Max Act: 2.7957. Min Act: -0.0000

Data Index: 708228 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 6.1688. Min Range: -6.1688

Max Act: 2.9112. Min Act: 0.0000

Data Index: 156066 (C4 (Web Text))

Max Activating Token Index: 112