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

Dataset: The Pile

Neuron 4593 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1977073 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.6632. Min Act: -0.0000

Data Index: 68545 (The Pile)

Max Activating Token Index: 711

Text #2

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5671. Min Act: -0.0000

Data Index: 592652 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1199344 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1508203 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1928448 (The Pile)

Max Activating Token Index: 349

Text #6

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1815546 (The Pile)

Max Activating Token Index: 655

Text #7

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5360. Min Act: -0.0000

Data Index: 308111 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5748. Min Act: -0.0000

Data Index: 905745 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5266. Min Act: -0.0000

Data Index: 391712 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5028. Min Act: -0.0000

Data Index: 417459 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5368. Min Act: -0.0000

Data Index: 755641 (The Pile)

Max Activating Token Index: 392

Text #12

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4930. Min Act: -0.0000

Data Index: 914281 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1554312 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1116583 (The Pile)

Max Activating Token Index: 242

Text #15

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1581894 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1160571 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1715789 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.5069. Min Act: -0.0000

Data Index: 636464 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 0.7064. Min Range: -0.7064

Max Act: 0.4683. Min Act: -0.0000

Data Index: 332312 (The Pile)

Max Activating Token Index: 666