Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1431 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1128. Min Range: -1.1128

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1468730 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 1.1128. Min Range: -1.1128

Max Act: 1.0553. Min Act: -0.0000

Data Index: 197553 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.9585. Min Act: -0.0000

Data Index: 146406 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1058100 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8744. Min Act: -0.0000

Data Index: 994740 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1546620 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1461236 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7799. Min Act: -0.0000

Data Index: 824307 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1783157 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7790. Min Act: -0.0000

Data Index: 462280 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7258. Min Act: -0.0000

Data Index: 190785 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7476. Min Act: -0.0000

Data Index: 881328 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8075. Min Act: -0.0000

Data Index: 723951 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1511421 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1607345 (The Pile)

Max Activating Token Index: 892

Text #15

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7368. Min Act: -0.0000

Data Index: 164380 (The Pile)

Max Activating Token Index: 336

Text #16

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.8505. Min Act: -0.0000

Data Index: 424486 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1254939 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1258556 (The Pile)

Max Activating Token Index: 512

Text #19

Max Range: 1.1128. Min Range: -1.1128

Max Act: 0.6973. Min Act: -0.0000

Data Index: 730842 (The Pile)

Max Activating Token Index: 471