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

Dataset: The Pile

Neuron 1133 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: 1.2981. Min Range: -1.2981

Max Act: 1.2981. Min Act: -0.0000

Data Index: 144279 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2071. Min Act: -0.0000

Data Index: 702658 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1613894 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0192. Min Act: -0.0000

Data Index: 792763 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1260355 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1928844 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9514. Min Act: -0.0000

Data Index: 332524 (The Pile)

Max Activating Token Index: 298

Text #7

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8823. Min Act: -0.0000

Data Index: 467715 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1938251 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9020. Min Act: -0.0000

Data Index: 934662 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1444783 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1135941 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1882720 (The Pile)

Max Activating Token Index: 690

Text #13

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.7942. Min Act: -0.0000

Data Index: 936907 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1273595 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8321. Min Act: -0.0000

Data Index: 594302 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.7929. Min Act: -0.0000

Data Index: 760706 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1789710 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.7809. Min Act: -0.0000

Data Index: 438008 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1954885 (The Pile)

Max Activating Token Index: 803