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

Dataset: The Pile

Neuron 3300 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: 0.4654. Min Range: -0.4654

Max Act: 0.4093. Min Act: -0.0000

Data Index: 768848 (The Pile)

Max Activating Token Index: 920

Text #1

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1903649 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.4099. Min Act: -0.0000

Data Index: 85115 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3996. Min Act: -0.0000

Data Index: 531358 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3876. Min Act: -0.0000

Data Index: 187737 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1105290 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3948. Min Act: -0.0000

Data Index: 782507 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3891. Min Act: -0.0000

Data Index: 811486 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1759005 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3768. Min Act: -0.0000

Data Index: 220555 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1427434 (The Pile)

Max Activating Token Index: 883

Text #11

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3511. Min Act: -0.0000

Data Index: 693811 (The Pile)

Max Activating Token Index: 519

Text #12

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1427720 (The Pile)

Max Activating Token Index: 879

Text #13

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1886433 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1139485 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3315. Min Act: -0.0000

Data Index: 636624 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3598. Min Act: -0.0000

Data Index: 515877 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3327. Min Act: -0.0000

Data Index: 836340 (The Pile)

Max Activating Token Index: 876

Text #18

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3262. Min Act: -0.0000

Data Index: 635628 (The Pile)

Max Activating Token Index: 721

Text #19

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1555607 (The Pile)

Max Activating Token Index: 914