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

Dataset: The Pile

Neuron 234 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: 0.8040. Min Range: -0.8040

Max Act: 0.7742. Min Act: -0.0000

Data Index: 169868 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7702. Min Act: -0.0000

Data Index: 414910 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1905028 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1957428 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7050. Min Act: -0.0000

Data Index: 672957 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1971412 (The Pile)

Max Activating Token Index: 906

Text #6

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1598380 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7036. Min Act: -0.0000

Data Index: 459240 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1205105 (The Pile)

Max Activating Token Index: 563

Text #9

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.7079. Min Act: -0.0000

Data Index: 465680 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1012232 (The Pile)

Max Activating Token Index: 4

Text #11

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1032805 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6954. Min Act: -0.0000

Data Index: 280123 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6292. Min Act: -0.0000

Data Index: 936645 (The Pile)

Max Activating Token Index: 947

Text #14

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6499. Min Act: 0.0000

Data Index: 856389 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6827. Min Act: -0.0000

Data Index: 402466 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1079833 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1331423 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1723939 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 0.8040. Min Range: -0.8040

Max Act: 0.6454. Min Act: -0.0000

Data Index: 334993 (The Pile)

Max Activating Token Index: 661