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

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

Neuron 5058 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.6747. Min Act: -0.0000

Data Index: 215207 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.6207. Min Act: -0.0000

Data Index: 149342 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.5841. Min Act: -0.0000

Data Index: 214014 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.6679. Min Act: -0.0000

Data Index: 506666 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.5852. Min Act: -0.0000

Data Index: 1224354 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.4038. Min Act: -0.0000

Data Index: 19460 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.3993. Min Act: -0.0000

Data Index: 73310 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.4122. Min Act: -0.0000

Data Index: 579834 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.3299. Min Act: -0.0000

Data Index: 1250400 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.1652. Min Act: -0.0000

Data Index: 7730 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.2316. Min Act: -0.0000

Data Index: 1000795 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.1823. Min Act: -0.0000

Data Index: 990797 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.2713. Min Act: -0.0000

Data Index: 515606 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1000077 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1199067 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.1203. Min Act: -0.0000

Data Index: 931482 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1294827 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.1576. Min Act: -0.0000

Data Index: 571810 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1308980 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.6747. Min Range: -1.6747

Max Act: 1.1591. Min Act: -0.0000

Data Index: 587525 (C4 (Web Text))

Max Activating Token Index: 257