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

Dataset: The Pile

Neuron 4356 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: 0.5772. Min Range: -0.5772

Max Act: 0.5772. Min Act: -0.0000

Data Index: 7462 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1202728 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5294. Min Act: -0.0000

Data Index: 267618 (The Pile)

Max Activating Token Index: 32

Text #3

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1145709 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5447. Min Act: -0.0000

Data Index: 163496 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4932. Min Act: -0.0000

Data Index: 615352 (The Pile)

Max Activating Token Index: 906

Text #6

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4901. Min Act: -0.0000

Data Index: 449165 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5364. Min Act: -0.0000

Data Index: 525610 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1266203 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1363777 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4922. Min Act: -0.0000

Data Index: 274218 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4917. Min Act: -0.0000

Data Index: 935315 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1104738 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4684. Min Act: -0.0000

Data Index: 373434 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1994330 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4606. Min Act: -0.0000

Data Index: 762070 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4609. Min Act: -0.0000

Data Index: 792697 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1871888 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4419. Min Act: -0.0000

Data Index: 780857 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4400. Min Act: -0.0000

Data Index: 270723 (The Pile)

Max Activating Token Index: 366