Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 23 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6157. Min Act: -0.1700

Data Index: 1420588 (Open Web Text)

Max Activating Token Index: 730

Text #1

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6797. Min Act: -0.1700

Data Index: 265782 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6359. Min Act: -0.1700

Data Index: 6923557 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6054. Min Act: -0.1700

Data Index: 3325855 (Open Web Text)

Max Activating Token Index: 594

Text #4

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5894. Min Act: -0.1700

Data Index: 4710343 (Open Web Text)

Max Activating Token Index: 92

Text #5

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5889. Min Act: -0.1700

Data Index: 6174328 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6280. Min Act: -0.1700

Data Index: 649571 (Open Web Text)

Max Activating Token Index: 776

Text #7

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5561. Min Act: -0.1700

Data Index: 7343862 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5573. Min Act: -0.1700

Data Index: 1883784 (Open Web Text)

Max Activating Token Index: 506

Text #9

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5716. Min Act: -0.1700

Data Index: 2450299 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5632. Min Act: -0.1700

Data Index: 4228846 (Open Web Text)

Max Activating Token Index: 860

Text #11

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5741. Min Act: -0.1700

Data Index: 2099050 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5222. Min Act: -0.1700

Data Index: 3801672 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5108. Min Act: -0.1700

Data Index: 2745635 (Open Web Text)

Max Activating Token Index: 470

Text #14

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5426. Min Act: -0.1700

Data Index: 712166 (Open Web Text)

Max Activating Token Index: 152

Text #15

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5383. Min Act: -0.1700

Data Index: 987844 (Open Web Text)

Max Activating Token Index: 484

Text #16

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1977986 (Open Web Text)

Max Activating Token Index: 447

Text #17

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5319. Min Act: -0.1700

Data Index: 4639254 (Open Web Text)

Max Activating Token Index: 461

Text #18

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5500. Min Act: -0.1700

Data Index: 5132372 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5509. Min Act: -0.1700

Data Index: 2039089 (Open Web Text)

Max Activating Token Index: 652