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

Dataset: The Pile

Neuron 4118 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0847. Min Act: -0.0000

Data Index: 259820 (The Pile)

Max Activating Token Index: 901

Text #1

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0924. Min Act: 0.0000

Data Index: 746505 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8666. Min Act: -0.0000

Data Index: 375040 (The Pile)

Max Activating Token Index: 19

Text #3

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1351894 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8674. Min Act: -0.0000

Data Index: 799260 (The Pile)

Max Activating Token Index: 867

Text #5

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1035934 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8806. Min Act: -0.0000

Data Index: 151452 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8652. Min Act: -0.0000

Data Index: 233381 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8722. Min Act: -0.0000

Data Index: 539249 (The Pile)

Max Activating Token Index: 5

Text #9

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1083674 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7739. Min Act: -0.0000

Data Index: 703287 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1042758 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1332306 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8519. Min Act: -0.0000

Data Index: 736903 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7984. Min Act: -0.0000

Data Index: 360434 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1190576 (The Pile)

Max Activating Token Index: 24

Text #16

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8123. Min Act: -0.0000

Data Index: 693780 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1756340 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8085. Min Act: -0.0000

Data Index: 134580 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8319. Min Act: -0.0000

Data Index: 488575 (The Pile)

Max Activating Token Index: 506