Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3212 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4165. Min Act: -0.0000

Data Index: 756648 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2893. Min Act: -0.0000

Data Index: 309431 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3000. Min Act: 0.0000

Data Index: 655167 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1556875 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1046641 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1529511 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1788446 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2455. Min Act: -0.0000

Data Index: 105553 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1549004 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1947694 (The Pile)

Max Activating Token Index: 237

Text #10

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2412. Min Act: 0.0000

Data Index: 1070797 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1214679 (The Pile)

Max Activating Token Index: 893

Text #12

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2388. Min Act: -0.0000

Data Index: 231449 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2250. Min Act: -0.0000

Data Index: 889571 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1281244 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2262. Min Act: -0.0000

Data Index: 264109 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1054414 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1461734 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2178. Min Act: 0.0000

Data Index: 1395085 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2332. Min Act: -0.0000

Data Index: 380605 (The Pile)

Max Activating Token Index: 755