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

Dataset: The Pile

Neuron 4078 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3584. Min Act: -0.0000

Data Index: 419660 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3034. Min Act: -0.0000

Data Index: 194591 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.4445. Min Act: -0.0000

Data Index: 864104 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3722. Min Act: -0.0000

Data Index: 713097 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2509. Min Act: -0.0000

Data Index: 264463 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1671773 (The Pile)

Max Activating Token Index: 351

Text #6

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2604. Min Act: -0.0000

Data Index: 755436 (The Pile)

Max Activating Token Index: 274

Text #7

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3276. Min Act: -0.0000

Data Index: 1993159 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3974. Min Act: -0.0000

Data Index: 475710 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3432. Min Act: -0.0000

Data Index: 1037597 (The Pile)

Max Activating Token Index: 562

Text #10

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.1717. Min Act: -0.0000

Data Index: 357623 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3003. Min Act: -0.0000

Data Index: 1239764 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1590575 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3849. Min Act: -0.0000

Data Index: 181190 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1936492 (The Pile)

Max Activating Token Index: 117

Text #15

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1044046 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1236538 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1881632 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.8916. Min Act: -0.0000

Data Index: 1742823 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.1446. Min Act: -0.0000

Data Index: 509831 (The Pile)

Max Activating Token Index: 478