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

Dataset: The Pile

Neuron 1384 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: 1.1092. Min Range: -1.1092

Max Act: 1.1092. Min Act: -0.0000

Data Index: 18682 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 1.1092. Min Range: -1.1092

Max Act: 1.0766. Min Act: -0.0000

Data Index: 25712 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.1092. Min Range: -1.1092

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1679328 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 1.1092. Min Range: -1.1092

Max Act: 1.0141. Min Act: -0.0000

Data Index: 257176 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1059135 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9245. Min Act: -0.0000

Data Index: 711955 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9492. Min Act: -0.0000

Data Index: 465345 (The Pile)

Max Activating Token Index: 127

Text #7

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1394297 (The Pile)

Max Activating Token Index: 703

Text #8

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1398903 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1856089 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8901. Min Act: -0.0000

Data Index: 209406 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1999653 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9487. Min Act: -0.0000

Data Index: 868954 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1972770 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1793496 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8204. Min Act: -0.0000

Data Index: 974972 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8339. Min Act: -0.0000

Data Index: 563738 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8287. Min Act: -0.0000

Data Index: 770435 (The Pile)

Max Activating Token Index: 857

Text #18

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1168090 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1041186 (The Pile)

Max Activating Token Index: 504