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

Dataset: The Pile

Neuron 3559 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.9500. Min Act: -0.0000

Data Index: 1481699 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.6151. Min Act: -0.0000

Data Index: 1078539 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1810797 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4015. Min Act: -0.0000

Data Index: 1694087 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4472. Min Act: -0.0000

Data Index: 15182 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4713. Min Act: -0.0000

Data Index: 251240 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3652. Min Act: -0.0000

Data Index: 105331 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3220. Min Act: -0.0000

Data Index: 1939134 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3923. Min Act: -0.0000

Data Index: 1608902 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3688. Min Act: -0.0000

Data Index: 1276712 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4466. Min Act: -0.0000

Data Index: 367016 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3254. Min Act: -0.0000

Data Index: 814751 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.3767. Min Act: -0.0000

Data Index: 692572 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1766964 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.2982. Min Act: -0.0000

Data Index: 1502686 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.2606. Min Act: -0.0000

Data Index: 531854 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.2798. Min Act: -0.0000

Data Index: 723305 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.2661. Min Act: -0.0000

Data Index: 336080 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.1952. Min Act: -0.0000

Data Index: 721329 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 1.9500. Min Range: -1.9500

Max Act: 1.4241. Min Act: -0.0000

Data Index: 533012 (The Pile)

Max Activating Token Index: 109