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

Dataset: The Pile

Neuron 3232 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: 2.1949. Min Range: -2.1949

Max Act: 2.1949. Min Act: -0.0000

Data Index: 1964645 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 2.1949. Min Range: -2.1949

Max Act: 2.1769. Min Act: -0.0000

Data Index: 434968 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.9371. Min Act: -0.0000

Data Index: 1428912 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5799. Min Act: -0.0000

Data Index: 1599448 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.8062. Min Act: -0.0000

Data Index: 1830812 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.6774. Min Act: -0.0000

Data Index: 1799090 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4576. Min Act: -0.0000

Data Index: 199440 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5597. Min Act: -0.0000

Data Index: 1200810 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4739. Min Act: -0.0000

Data Index: 194224 (The Pile)

Max Activating Token Index: 984

Text #9

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5408. Min Act: -0.0000

Data Index: 374484 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5353. Min Act: -0.0000

Data Index: 4182 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4173. Min Act: -0.0000

Data Index: 941891 (The Pile)

Max Activating Token Index: 704

Text #12

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5002. Min Act: -0.0000

Data Index: 1154817 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4188. Min Act: -0.0000

Data Index: 531258 (The Pile)

Max Activating Token Index: 715

Text #14

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.3734. Min Act: -0.0000

Data Index: 1154471 (The Pile)

Max Activating Token Index: 444

Text #15

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.4118. Min Act: -0.0000

Data Index: 331433 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.3367. Min Act: -0.0000

Data Index: 1111707 (The Pile)

Max Activating Token Index: 578

Text #17

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.5862. Min Act: -0.0000

Data Index: 986087 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.2522. Min Act: -0.0000

Data Index: 605139 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 2.1949. Min Range: -2.1949

Max Act: 1.3853. Min Act: -0.0000

Data Index: 949849 (The Pile)

Max Activating Token Index: 70