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

Dataset: The Pile

Neuron 208 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.6325. Min Act: -0.0000

Data Index: 661375 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5917. Min Act: -0.0000

Data Index: 1638584 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1582455 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5134. Min Act: -0.0000

Data Index: 1170479 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1518692 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.2695. Min Act: -0.0000

Data Index: 922927 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.1966. Min Act: -0.0000

Data Index: 1373991 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1251729 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.1009. Min Act: -0.0000

Data Index: 133456 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1398399 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.1732. Min Act: -0.0000

Data Index: 924429 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1548819 (The Pile)

Max Activating Token Index: 358

Text #12

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.0823. Min Act: -0.0000

Data Index: 521485 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 1.6325. Min Range: -1.6325

Max Act: 0.9548. Min Act: -0.0000

Data Index: 239974 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 1.6325. Min Range: -1.6325

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1780124 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 1.6325. Min Range: -1.6325

Max Act: 0.9643. Min Act: -0.0000

Data Index: 592717 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 1.6325. Min Range: -1.6325

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1810315 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 1.6325. Min Range: -1.6325

Max Act: 0.9841. Min Act: -0.0000

Data Index: 168835 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.0150. Min Act: -0.0000

Data Index: 1802147 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 1.6325. Min Range: -1.6325

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1960733 (The Pile)

Max Activating Token Index: 811