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

Dataset: The Pile

Neuron 2231 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: 1.7021. Min Range: -1.7021

Max Act: 1.7021. Min Act: -0.0000

Data Index: 724688 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 1.7021. Min Range: -1.7021

Max Act: 1.5186. Min Act: -0.0000

Data Index: 1692641 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 1.7021. Min Range: -1.7021

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1013818 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 1.7021. Min Range: -1.7021

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1560588 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.9677. Min Act: -0.0000

Data Index: 495059 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 1.7021. Min Range: -1.7021

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1063983 (The Pile)

Max Activating Token Index: 128

Text #6

Max Range: 1.7021. Min Range: -1.7021

Max Act: 1.0510. Min Act: -0.0000

Data Index: 764051 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 1.7021. Min Range: -1.7021

Max Act: 1.1040. Min Act: -0.0000

Data Index: 631001 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1981651 (The Pile)

Max Activating Token Index: 128

Text #9

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1510048 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 1.7021. Min Range: -1.7021

Max Act: 1.0033. Min Act: -0.0000

Data Index: 480726 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 1.7021. Min Range: -1.7021

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1751269 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 1.7021. Min Range: -1.7021

Max Act: 1.0421. Min Act: -0.0000

Data Index: 545349 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.9765. Min Act: -0.0000

Data Index: 1174352 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1077470 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1361200 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1695127 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1519250 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1878913 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 1.7021. Min Range: -1.7021

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1965778 (The Pile)

Max Activating Token Index: 719