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

Dataset: The Pile

Neuron 1020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1967708 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.4264. Min Act: -0.0000

Data Index: 936920 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3992. Min Act: -0.0000

Data Index: 211638 (The Pile)

Max Activating Token Index: 644

Text #3

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1040695 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3589. Min Act: -0.0000

Data Index: 647738 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1989862 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1365025 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3286. Min Act: -0.0000

Data Index: 910952 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3397. Min Act: -0.0000

Data Index: 576295 (The Pile)

Max Activating Token Index: 950

Text #9

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1671366 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1770777 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3309. Min Act: -0.0000

Data Index: 258862 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3274. Min Act: -0.0000

Data Index: 164644 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3153. Min Act: -0.0000

Data Index: 755152 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1624256 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1022797 (The Pile)

Max Activating Token Index: 454

Text #16

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.2996. Min Act: -0.0000

Data Index: 188827 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1919050 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1731170 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 0.4841. Min Range: -0.4841

Max Act: 0.3108. Min Act: -0.0000

Data Index: 1116924 (The Pile)

Max Activating Token Index: 173