Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3730 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5502. Min Act: -0.0000

Data Index: 188035 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1274209 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1468253 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4545. Min Act: 0.0000

Data Index: 1465871 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4480. Min Act: -0.0000

Data Index: 129348 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1381985 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4311. Min Act: -0.0000

Data Index: 440391 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1241630 (The Pile)

Max Activating Token Index: 853

Text #8

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1800817 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1793256 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1410695 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4118. Min Act: 0.0000

Data Index: 157510 (The Pile)

Max Activating Token Index: 456

Text #12

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3799. Min Act: -0.0000

Data Index: 376033 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3921. Min Act: -0.0000

Data Index: 450911 (The Pile)

Max Activating Token Index: 216

Text #14

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3762. Min Act: -0.0000

Data Index: 411713 (The Pile)

Max Activating Token Index: 880

Text #15

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1855964 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3719. Min Act: 0.0000

Data Index: 1753710 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3819. Min Act: -0.0000

Data Index: 179703 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1173826 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.3560. Min Act: -0.0000

Data Index: 953085 (The Pile)

Max Activating Token Index: 808