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

Dataset: The Pile

Neuron 3943 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: 0.3733. Min Range: -0.3733

Max Act: 0.3588. Min Act: -0.0000

Data Index: 193926 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3733. Min Act: -0.0000

Data Index: 753934 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1797429 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3066. Min Act: -0.0000

Data Index: 534830 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1544535 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2933. Min Act: -0.0000

Data Index: 847297 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3084. Min Act: -0.0000

Data Index: 716318 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3045. Min Act: -0.0000

Data Index: 303784 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1194806 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2957. Min Act: -0.0000

Data Index: 329690 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1514179 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2963. Min Act: -0.0000

Data Index: 657597 (The Pile)

Max Activating Token Index: 835

Text #12

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2661. Min Act: -0.0000

Data Index: 737317 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3186. Min Act: -0.0000

Data Index: 321309 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2716. Min Act: -0.0000

Data Index: 577311 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1065030 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2405. Min Act: -0.0000

Data Index: 582807 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1829886 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2864. Min Act: -0.0000

Data Index: 742176 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1243036 (The Pile)

Max Activating Token Index: 185