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

Dataset: The Pile

Neuron 2929 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.1397. Min Act: -0.0000

Data Index: 838537 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1935853 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9769. Min Act: -0.0000

Data Index: 706132 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1331562 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8715. Min Act: -0.0000

Data Index: 891422 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1487994 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9022. Min Act: -0.0000

Data Index: 512771 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9321. Min Act: -0.0000

Data Index: 826411 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9170. Min Act: -0.0000

Data Index: 912490 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8926. Min Act: -0.0000

Data Index: 623569 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1077076 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1233583 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8488. Min Act: -0.0000

Data Index: 749619 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1571893 (The Pile)

Max Activating Token Index: 78

Text #14

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8639. Min Act: -0.0000

Data Index: 896428 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8550. Min Act: -0.0000

Data Index: 512359 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8035. Min Act: -0.0000

Data Index: 966734 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1887074 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7935. Min Act: -0.0000

Data Index: 507951 (The Pile)

Max Activating Token Index: 77

Text #19

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1729773 (The Pile)

Max Activating Token Index: 359