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

Dataset: The Pile

Neuron 618 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: 4.1915. Min Range: -4.1915

Max Act: 4.1915. Min Act: -0.0000

Data Index: 1556536 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.7441. Min Act: -0.0000

Data Index: 1855972 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.6816. Min Act: -0.0000

Data Index: 1867134 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.6346. Min Act: -0.0000

Data Index: 1034776 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.6398. Min Act: -0.0000

Data Index: 512479 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.5545. Min Act: -0.0000

Data Index: 825959 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.5369. Min Act: -0.0000

Data Index: 561762 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.3451. Min Act: -0.0000

Data Index: 1488357 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.5034. Min Act: -0.0000

Data Index: 1778976 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.4974. Min Act: -0.0000

Data Index: 1622133 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.3492. Min Act: -0.0000

Data Index: 542013 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.4993. Min Act: -0.0000

Data Index: 370207 (The Pile)

Max Activating Token Index: 431

Text #12

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.2896. Min Act: -0.0000

Data Index: 1716838 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.4471. Min Act: -0.0000

Data Index: 1407609 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.6193. Min Act: -0.0000

Data Index: 974169 (The Pile)

Max Activating Token Index: 117

Text #15

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.1639. Min Act: -0.0000

Data Index: 942510 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.4352. Min Act: -0.0000

Data Index: 928896 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.2929. Min Act: -0.0000

Data Index: 1262281 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.4235. Min Act: -0.0000

Data Index: 1317454 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 4.1915. Min Range: -4.1915

Max Act: 3.4250. Min Act: -0.0000

Data Index: 87087 (The Pile)

Max Activating Token Index: 791