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

Dataset: The Pile

Neuron 534 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: 3.2040. Min Range: -3.2040

Max Act: 3.2040. Min Act: -0.0000

Data Index: 1393911 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.8910. Min Act: -0.0000

Data Index: 1624093 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.9787. Min Act: -0.0000

Data Index: 1451228 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.9205. Min Act: -0.0000

Data Index: 1249430 (The Pile)

Max Activating Token Index: 880

Text #4

Max Range: 3.2040. Min Range: -3.2040

Max Act: 3.1845. Min Act: -0.0000

Data Index: 774261 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 3.2040. Min Range: -3.2040

Max Act: 3.0515. Min Act: -0.0000

Data Index: 350794 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.9000. Min Act: -0.0000

Data Index: 1850032 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6595. Min Act: -0.0000

Data Index: 1905168 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.8577. Min Act: -0.0000

Data Index: 1493092 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6294. Min Act: -0.0000

Data Index: 480605 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.7353. Min Act: -0.0000

Data Index: 1184314 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6429. Min Act: -0.0000

Data Index: 886500 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6372. Min Act: -0.0000

Data Index: 1623558 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6903. Min Act: -0.0000

Data Index: 195993 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6260. Min Act: -0.0000

Data Index: 1767573 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.5590. Min Act: -0.0000

Data Index: 76436 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.9159. Min Act: -0.0000

Data Index: 1813376 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6817. Min Act: -0.0000

Data Index: 358604 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6094. Min Act: -0.0000

Data Index: 1822917 (The Pile)

Max Activating Token Index: 602

Text #19

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6510. Min Act: -0.0000

Data Index: 804533 (The Pile)

Max Activating Token Index: 327