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

Dataset: The Pile

Neuron 3335 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: 0.5770. Min Range: -0.5770

Max Act: 0.5770. Min Act: -0.0000

Data Index: 827896 (The Pile)

Max Activating Token Index: 762

Text #1

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1661159 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4590. Min Act: -0.0000

Data Index: 323067 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4929. Min Act: -0.0000

Data Index: 245086 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5392. Min Act: -0.0000

Data Index: 108092 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4820. Min Act: -0.0000

Data Index: 466892 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5306. Min Act: -0.0000

Data Index: 919686 (The Pile)

Max Activating Token Index: 558

Text #7

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1270043 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5177. Min Act: -0.0000

Data Index: 862769 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5476. Min Act: -0.0000

Data Index: 560309 (The Pile)

Max Activating Token Index: 710

Text #10

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4600. Min Act: -0.0000

Data Index: 927530 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.3876. Min Act: -0.0000

Data Index: 623290 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1570864 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1368730 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1345847 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1710765 (The Pile)

Max Activating Token Index: 835

Text #16

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1355093 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1605767 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1678146 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 0.5770. Min Range: -0.5770

Max Act: 0.5507. Min Act: -0.0000

Data Index: 967292 (The Pile)

Max Activating Token Index: 353