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

Dataset: The Pile

Neuron 1879 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1505043 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8875. Min Act: -0.0000

Data Index: 127687 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.5602. Min Act: -0.0000

Data Index: 787500 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1620712 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4975. Min Act: -0.0000

Data Index: 205934 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4610. Min Act: -0.0000

Data Index: 463506 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1510889 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1093313 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1420232 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1783396 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4065. Min Act: -0.0000

Data Index: 924850 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1454594 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1828260 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1115060 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1037248 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.4050. Min Act: -0.0000

Data Index: 221404 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.3636. Min Act: -0.0000

Data Index: 218432 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1280637 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.3793. Min Act: -0.0000

Data Index: 825271 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.3816. Min Act: -0.0000

Data Index: 366053 (The Pile)

Max Activating Token Index: 438