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

Dataset: The Pile

Neuron 602 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.8368. Min Act: -0.0000

Data Index: 648737 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.9126. Min Act: -0.0000

Data Index: 1913008 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.4971. Min Act: -0.0000

Data Index: 1739228 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.3378. Min Act: -0.0000

Data Index: 1737208 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.6178. Min Act: -0.0000

Data Index: 1654955 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.4474. Min Act: -0.0000

Data Index: 580857 (The Pile)

Max Activating Token Index: 242

Text #6

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.4302. Min Act: -0.0000

Data Index: 553433 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.5415. Min Act: -0.0000

Data Index: 162440 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.3854. Min Act: -0.0000

Data Index: 1377143 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.3053. Min Act: -0.0000

Data Index: 1384858 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.4344. Min Act: -0.0000

Data Index: 120412 (The Pile)

Max Activating Token Index: 376

Text #11

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.3037. Min Act: -0.0000

Data Index: 25059 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.6978. Min Act: -0.0000

Data Index: 688922 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.3829. Min Act: -0.0000

Data Index: 1494289 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.2087. Min Act: -0.0000

Data Index: 912642 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.3641. Min Act: -0.0000

Data Index: 1447557 (The Pile)

Max Activating Token Index: 700

Text #16

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.4343. Min Act: -0.0000

Data Index: 146484 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.2882. Min Act: -0.0000

Data Index: 621734 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.2927. Min Act: -0.0000

Data Index: 755291 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 3.9126. Min Range: -3.9126

Max Act: 3.2838. Min Act: -0.0000

Data Index: 721705 (The Pile)

Max Activating Token Index: 800