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

Dataset: The Pile

Neuron 2823 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: 0.6798. Min Range: -0.6798

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1910734 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1719146 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1894111 (The Pile)

Max Activating Token Index: 883

Text #3

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1061733 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5846. Min Act: -0.0000

Data Index: 629310 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.6276. Min Act: -0.0000

Data Index: 941849 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1377427 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5550. Min Act: -0.0000

Data Index: 750697 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1540734 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5375. Min Act: -0.0000

Data Index: 840086 (The Pile)

Max Activating Token Index: 457

Text #10

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1492362 (The Pile)

Max Activating Token Index: 339

Text #11

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1471709 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.3510. Min Act: -0.0000

Data Index: 379042 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1441624 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1489957 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.3129. Min Act: -0.0000

Data Index: 817032 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1789813 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.3021. Min Act: -0.0000

Data Index: 400867 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1006522 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1457702 (The Pile)

Max Activating Token Index: 242