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

Dataset: The Pile

Neuron 3068 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: 1.0068. Min Range: -1.0068

Max Act: 1.0068. Min Act: -0.0000

Data Index: 851276 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.9101. Min Act: -0.0000

Data Index: 83637 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1013527 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8086. Min Act: -0.0000

Data Index: 207072 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1617356 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8040. Min Act: -0.0000

Data Index: 747471 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1331411 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7857. Min Act: 0.0000

Data Index: 976474 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7600. Min Act: -0.0000

Data Index: 107418 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1328919 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7463. Min Act: -0.0000

Data Index: 977123 (The Pile)

Max Activating Token Index: 209

Text #11

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1508448 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7283. Min Act: -0.0000

Data Index: 223742 (The Pile)

Max Activating Token Index: 954

Text #13

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7285. Min Act: -0.0000

Data Index: 429533 (The Pile)

Max Activating Token Index: 39

Text #14

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1075892 (The Pile)

Max Activating Token Index: 866

Text #15

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7118. Min Act: -0.0000

Data Index: 291241 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1426188 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1849944 (The Pile)

Max Activating Token Index: 855

Text #18

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6913. Min Act: 0.0000

Data Index: 1198060 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7023. Min Act: -0.0000

Data Index: 625187 (The Pile)

Max Activating Token Index: 134