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

Dataset: The Pile

Neuron 4642 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: 0.4635. Min Range: -0.4635

Max Act: 0.4618. Min Act: -0.0000

Data Index: 955507 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1198824 (The Pile)

Max Activating Token Index: 304

Text #2

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1718444 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4635. Min Act: -0.0000

Data Index: 492972 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4284. Min Act: -0.0000

Data Index: 525425 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4097. Min Act: -0.0000

Data Index: 497191 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1671605 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4134. Min Act: -0.0000

Data Index: 698350 (The Pile)

Max Activating Token Index: 800

Text #8

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4085. Min Act: -0.0000

Data Index: 893043 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1471451 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4050. Min Act: -0.0000

Data Index: 795220 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1127705 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3826. Min Act: -0.0000

Data Index: 874019 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1738835 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3944. Min Act: -0.0000

Data Index: 972610 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1435605 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1860769 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4330. Min Act: -0.0000

Data Index: 679322 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4075. Min Act: -0.0000

Data Index: 371339 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1722694 (The Pile)

Max Activating Token Index: 77