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

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

Neuron 1714 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.1607. Min Act: -0.0000

Data Index: 958359 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0833. Min Act: -0.0000

Data Index: 1036734 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1237354 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9481. Min Act: -0.0000

Data Index: 149094 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0508. Min Act: -0.0000

Data Index: 42695 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8918. Min Act: -0.0000

Data Index: 646779 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8646. Min Act: -0.0000

Data Index: 255697 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8105. Min Act: -0.0000

Data Index: 374240 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8629. Min Act: -0.0000

Data Index: 314935 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8353. Min Act: -0.0000

Data Index: 127884 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1038891 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1051630 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1229294 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8065. Min Act: -0.0000

Data Index: 146763 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1321303 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8254. Min Act: -0.0000

Data Index: 724069 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8319. Min Act: -0.0000

Data Index: 306613 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8037. Min Act: -0.0000

Data Index: 4608 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1143083 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1019993 (C4 (Web Text))

Max Activating Token Index: 747