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

Dataset: The Pile

Neuron 321 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1012189 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5065. Min Act: -0.0000

Data Index: 778888 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1340713 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1867787 (The Pile)

Max Activating Token Index: 424

Text #4

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4785. Min Act: -0.0000

Data Index: 809510 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4845. Min Act: -0.0000

Data Index: 118465 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4498. Min Act: -0.0000

Data Index: 609816 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4599. Min Act: -0.0000

Data Index: 847814 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1650181 (The Pile)

Max Activating Token Index: 683

Text #9

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4332. Min Act: -0.0000

Data Index: 21191 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1843946 (The Pile)

Max Activating Token Index: 462

Text #11

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1124122 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1609001 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1070273 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4699. Min Act: -0.0000

Data Index: 110896 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4252. Min Act: -0.0000

Data Index: 346466 (The Pile)

Max Activating Token Index: 441

Text #16

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1163527 (The Pile)

Max Activating Token Index: 460

Text #17

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1084948 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1785578 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.3932. Min Act: -0.0000

Data Index: 539172 (The Pile)

Max Activating Token Index: 56