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

Dataset: The Pile

Neuron 2022 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: 0.9649. Min Range: -0.9649

Max Act: 0.9649. Min Act: -0.0000

Data Index: 121928 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1808156 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8837. Min Act: -0.0000

Data Index: 938248 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8100. Min Act: 0.0000

Data Index: 1707214 (The Pile)

Max Activating Token Index: 72

Text #4

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8760. Min Act: -0.0000

Data Index: 348407 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1376506 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7755. Min Act: -0.0000

Data Index: 31545 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7757. Min Act: -0.0000

Data Index: 371696 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1455762 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1879649 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7485. Min Act: -0.0000

Data Index: 686521 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7434. Min Act: -0.0000

Data Index: 716633 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1049771 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1312090 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1166144 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1489665 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7273. Min Act: -0.0000

Data Index: 514899 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6785. Min Act: -0.0000

Data Index: 77188 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1505931 (The Pile)

Max Activating Token Index: 714

Text #19

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1346925 (The Pile)

Max Activating Token Index: 187