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

Dataset: The Pile

Neuron 3750 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4371. Min Act: -0.0000

Data Index: 375322 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4752. Min Act: -0.0000

Data Index: 801701 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1212432 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1204142 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4788. Min Act: -0.0000

Data Index: 162830 (The Pile)

Max Activating Token Index: 716

Text #5

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3808. Min Act: -0.0000

Data Index: 831126 (The Pile)

Max Activating Token Index: 869

Text #6

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4221. Min Act: -0.0000

Data Index: 814717 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1640847 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4639. Min Act: -0.0000

Data Index: 990890 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3493. Min Act: -0.0000

Data Index: 740504 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3988. Min Act: -0.0001

Data Index: 243097 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1109872 (The Pile)

Max Activating Token Index: 871

Text #12

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1794649 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3641. Min Act: -0.0000

Data Index: 345295 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3959. Min Act: -0.0000

Data Index: 655962 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3845. Min Act: -0.0000

Data Index: 471157 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1923649 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1278368 (The Pile)

Max Activating Token Index: 926

Text #18

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1049765 (The Pile)

Max Activating Token Index: 115

Text #19

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3748. Min Act: -0.0000

Data Index: 411026 (The Pile)

Max Activating Token Index: 817