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

Dataset: The Pile

Neuron 4434 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: 1.2720. Min Range: -1.2720

Max Act: 1.2720. Min Act: -0.0000

Data Index: 447655 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1457696 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.0462. Min Act: -0.0000

Data Index: 132755 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1465889 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1867213 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9433. Min Act: -0.0000

Data Index: 969001 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8742. Min Act: -0.0000

Data Index: 888784 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8448. Min Act: -0.0000

Data Index: 320354 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8868. Min Act: -0.0000

Data Index: 459835 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1024491 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1648940 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1125671 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8131. Min Act: -0.0000

Data Index: 630746 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1899297 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1204137 (The Pile)

Max Activating Token Index: 738

Text #15

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1262506 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1811276 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.7511. Min Act: -0.0000

Data Index: 341484 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1400828 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.7023. Min Act: -0.0000

Data Index: 13827 (The Pile)

Max Activating Token Index: 83