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

Dataset: The Pile

Neuron 2154 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: 3.8118. Min Range: -3.8118

Max Act: 3.8118. Min Act: 0.0000

Data Index: 1983024 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.7116. Min Act: 0.0000

Data Index: 196387 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.4205. Min Act: -0.0000

Data Index: 1709299 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.2189. Min Act: 0.0000

Data Index: 228440 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.3108. Min Act: -0.0000

Data Index: 1104611 (The Pile)

Max Activating Token Index: 388

Text #5

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.2733. Min Act: -0.0000

Data Index: 87986 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.2605. Min Act: 0.0000

Data Index: 956964 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.2515. Min Act: -0.0000

Data Index: 1325180 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.0778. Min Act: -0.0000

Data Index: 1782516 (The Pile)

Max Activating Token Index: 956

Text #9

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.3545. Min Act: -0.0000

Data Index: 1863802 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.1935. Min Act: -0.0000

Data Index: 1728451 (The Pile)

Max Activating Token Index: 956

Text #11

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.1612. Min Act: -0.0000

Data Index: 1618459 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.1592. Min Act: 0.0000

Data Index: 1201009 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.1565. Min Act: -0.0000

Data Index: 1492806 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.1470. Min Act: -0.0000

Data Index: 1895793 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 3.8118. Min Range: -3.8118

Max Act: 2.9837. Min Act: -0.0000

Data Index: 824795 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.1041. Min Act: 0.0000

Data Index: 1851712 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.0850. Min Act: -0.0000

Data Index: 223998 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.0598. Min Act: 0.0001

Data Index: 1005589 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 3.8118. Min Range: -3.8118

Max Act: 3.0287. Min Act: 0.0000

Data Index: 22487 (The Pile)

Max Activating Token Index: 647