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

Dataset: The Pile

Neuron 4699 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: 4.3718. Min Range: -4.3718

Max Act: 4.3718. Min Act: -0.0000

Data Index: 1009038 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.0886. Min Act: -0.0000

Data Index: 1805170 (The Pile)

Max Activating Token Index: 353

Text #2

Max Range: 4.3718. Min Range: -4.3718

Max Act: 4.0998. Min Act: -0.0000

Data Index: 1954866 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.9281. Min Act: -0.0000

Data Index: 1544474 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.4110. Min Act: -0.0000

Data Index: 1446622 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.4737. Min Act: -0.0000

Data Index: 1500688 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.3055. Min Act: -0.0000

Data Index: 1706000 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.6402. Min Act: -0.0000

Data Index: 188524 (The Pile)

Max Activating Token Index: 566

Text #8

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.3415. Min Act: -0.0000

Data Index: 284269 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.4787. Min Act: -0.0000

Data Index: 579045 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.2429. Min Act: -0.0000

Data Index: 1188489 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.2859. Min Act: -0.0000

Data Index: 577221 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.2292. Min Act: -0.0000

Data Index: 960539 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.5000. Min Act: -0.0000

Data Index: 1070811 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.1983. Min Act: -0.0000

Data Index: 1670320 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.1021. Min Act: -0.0000

Data Index: 835651 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.3044. Min Act: -0.0000

Data Index: 1441979 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 4.3718. Min Range: -4.3718

Max Act: 3.2193. Min Act: -0.0000

Data Index: 985739 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 4.3718. Min Range: -4.3718

Max Act: 2.9934. Min Act: -0.0000

Data Index: 159792 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 4.3718. Min Range: -4.3718

Max Act: 2.9470. Min Act: -0.0000

Data Index: 181103 (The Pile)

Max Activating Token Index: 201