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

Dataset: The Pile

Neuron 1929 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: 0.8749. Min Range: -0.8749

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1014828 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7556. Min Act: -0.0000

Data Index: 301811 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1692231 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1022196 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6803. Min Act: -0.0000

Data Index: 138579 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1932382 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6780. Min Act: -0.0000

Data Index: 773950 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6345. Min Act: -0.0000

Data Index: 599507 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6480. Min Act: -0.0000

Data Index: 560715 (The Pile)

Max Activating Token Index: 506

Text #9

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6561. Min Act: -0.0000

Data Index: 793629 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1049811 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1990577 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6138. Min Act: 0.0000

Data Index: 1054278 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1268794 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6120. Min Act: -0.0000

Data Index: 43688 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.5927. Min Act: 0.0000

Data Index: 1574748 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1911672 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1229060 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1407672 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 0.8749. Min Range: -0.8749

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1864634 (The Pile)

Max Activating Token Index: 615