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

Dataset: The Pile

Neuron 3314 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.9331. Min Act: -0.0000

Data Index: 866721 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.9620. Min Act: -0.0000

Data Index: 341153 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.8878. Min Act: -0.0000

Data Index: 812943 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1071039 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1073560 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1736953 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1291295 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6276. Min Act: -0.0000

Data Index: 759598 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6295. Min Act: -0.0000

Data Index: 371276 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1449401 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1162799 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1954739 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.3499. Min Act: -0.0000

Data Index: 752541 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.3433. Min Act: 0.0000

Data Index: 1813770 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.3042. Min Act: -0.0000

Data Index: 334273 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.3237. Min Act: -0.0000

Data Index: 718848 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.3776. Min Act: -0.0000

Data Index: 533322 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1542786 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.3059. Min Act: -0.0000

Data Index: 721424 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1826588 (The Pile)

Max Activating Token Index: 473