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

Dataset: The Pile

Neuron 4725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2613. Min Range: -3.2613

Max Act: 3.2613. Min Act: -0.0000

Data Index: 1520207 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.3494. Min Act: -0.0000

Data Index: 1374994 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.1602. Min Act: -0.0000

Data Index: 1848115 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.1661. Min Act: -0.0000

Data Index: 698194 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.1478. Min Act: -0.0000

Data Index: 842169 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.1656. Min Act: -0.0000

Data Index: 1318365 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.0125. Min Act: -0.0000

Data Index: 1673372 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.0525. Min Act: -0.0000

Data Index: 832834 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.0398. Min Act: -0.0000

Data Index: 1754724 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 3.2613. Min Range: -3.2613

Max Act: 1.7962. Min Act: -0.0000

Data Index: 1025745 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 3.2613. Min Range: -3.2613

Max Act: 1.9930. Min Act: -0.0000

Data Index: 459022 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.0667. Min Act: -0.0000

Data Index: 1214337 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 3.2613. Min Range: -3.2613

Max Act: 2.0064. Min Act: -0.0000

Data Index: 1400715 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 3.2613. Min Range: -3.2613

Max Act: 1.6850. Min Act: -0.0000

Data Index: 1986155 (The Pile)

Max Activating Token Index: 150

Text #14

Max Range: 3.2613. Min Range: -3.2613

Max Act: 1.6420. Min Act: -0.0000

Data Index: 1044550 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 3.2613. Min Range: -3.2613

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1008713 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 3.2613. Min Range: -3.2613

Max Act: 1.8191. Min Act: -0.0000

Data Index: 1792763 (The Pile)

Max Activating Token Index: 4

Text #17

Max Range: 3.2613. Min Range: -3.2613

Max Act: 1.8178. Min Act: -0.0000

Data Index: 1081076 (The Pile)

Max Activating Token Index: 137

Text #18

Max Range: 3.2613. Min Range: -3.2613

Max Act: 1.8079. Min Act: -0.0000

Data Index: 24707 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 3.2613. Min Range: -3.2613

Max Act: 1.5014. Min Act: -0.0000

Data Index: 959979 (The Pile)

Max Activating Token Index: 774