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

Dataset: The Pile

Neuron 2743 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2473. Min Range: -5.2473

Max Act: 5.1460. Min Act: -0.0000

Data Index: 724229 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 5.2473. Min Range: -5.2473

Max Act: 5.2473. Min Act: -0.0000

Data Index: 339432 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 5.2473. Min Range: -5.2473

Max Act: 4.6397. Min Act: -0.0000

Data Index: 1344991 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 5.2473. Min Range: -5.2473

Max Act: 4.9292. Min Act: -0.0000

Data Index: 181025 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 5.2473. Min Range: -5.2473

Max Act: 4.8166. Min Act: -0.0000

Data Index: 228428 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 5.2473. Min Range: -5.2473

Max Act: 4.3453. Min Act: -0.0000

Data Index: 582476 (The Pile)

Max Activating Token Index: 422

Text #6

Max Range: 5.2473. Min Range: -5.2473

Max Act: 4.3627. Min Act: -0.0000

Data Index: 793167 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 5.2473. Min Range: -5.2473

Max Act: 4.3551. Min Act: -0.0000

Data Index: 1306567 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.9977. Min Act: -0.0000

Data Index: 1833512 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 5.2473. Min Range: -5.2473

Max Act: 4.1608. Min Act: -0.0000

Data Index: 385330 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.7875. Min Act: -0.0000

Data Index: 1354544 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.8734. Min Act: -0.0000

Data Index: 738363 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.6280. Min Act: -0.0000

Data Index: 1959858 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.5617. Min Act: -0.0000

Data Index: 232779 (The Pile)

Max Activating Token Index: 348

Text #14

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.6134. Min Act: -0.0000

Data Index: 1140812 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.7449. Min Act: -0.0000

Data Index: 1090972 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.3694. Min Act: -0.0000

Data Index: 4235 (The Pile)

Max Activating Token Index: 30

Text #17

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.3134. Min Act: -0.0000

Data Index: 1847720 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.0162. Min Act: -0.0000

Data Index: 338253 (The Pile)

Max Activating Token Index: 986

Text #19

Max Range: 5.2473. Min Range: -5.2473

Max Act: 3.1085. Min Act: -0.0000

Data Index: 1684624 (The Pile)

Max Activating Token Index: 478