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

Dataset: The Pile

Neuron 3233 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: 0.5494. Min Range: -0.5494

Max Act: 0.5494. Min Act: -0.0000

Data Index: 313079 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4762. Min Act: -0.0000

Data Index: 583618 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1117380 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4870. Min Act: -0.0000

Data Index: 536024 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4132. Min Act: -0.0000

Data Index: 916533 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.3735. Min Act: -0.0000

Data Index: 907064 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4018. Min Act: -0.0000

Data Index: 607303 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4090. Min Act: -0.0000

Data Index: 256385 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1661048 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1056340 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1540529 (The Pile)

Max Activating Token Index: 580

Text #11

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.3363. Min Act: -0.0000

Data Index: 755590 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1219965 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.3484. Min Act: -0.0000

Data Index: 144213 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.2956. Min Act: -0.0000

Data Index: 905802 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1207051 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1938136 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1649012 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1423042 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1466098 (The Pile)

Max Activating Token Index: 865