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

Dataset: The Pile

Neuron 1248 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: 0.6159. Min Range: -0.6159

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1229837 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5580. Min Act: -0.0000

Data Index: 141985 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1425563 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1504633 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1187017 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1765532 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1747104 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1936847 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4581. Min Act: -0.0000

Data Index: 977284 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4465. Min Act: -0.0000

Data Index: 771958 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1771606 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1015019 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4346. Min Act: -0.0000

Data Index: 347121 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1418073 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4468. Min Act: -0.0000

Data Index: 834340 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4594. Min Act: -0.0000

Data Index: 376846 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1701993 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1546944 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1747357 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1991964 (The Pile)

Max Activating Token Index: 949