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

Dataset: The Pile

Neuron 834 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5890. Min Act: -0.0000

Data Index: 4140 (The Pile)

Max Activating Token Index: 981

Text #1

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4845. Min Act: -0.0000

Data Index: 551226 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4673. Min Act: -0.0000

Data Index: 786930 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1116981 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4483. Min Act: -0.0000

Data Index: 570038 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4455. Min Act: -0.0000

Data Index: 617374 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4247. Min Act: -0.0000

Data Index: 407488 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1696461 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1491347 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4287. Min Act: -0.0000

Data Index: 344002 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3942. Min Act: -0.0000

Data Index: 578964 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1227549 (The Pile)

Max Activating Token Index: 507

Text #12

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1306979 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4181. Min Act: -0.0000

Data Index: 760125 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1573542 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4014. Min Act: -0.0000

Data Index: 717734 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1616413 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1872990 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1546328 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3852. Min Act: -0.0000

Data Index: 141483 (The Pile)

Max Activating Token Index: 407