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

Dataset: Open Web Text

Neuron 1427 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: 4.8759. Min Range: -4.8759

Max Act: 4.8759. Min Act: -0.1700

Data Index: 3283502 (Open Web Text)

Max Activating Token Index: 404

Text #1

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.8043. Min Act: -0.1700

Data Index: 4026064 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7813. Min Act: -0.1700

Data Index: 5357736 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7816. Min Act: -0.1700

Data Index: 2415877 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7904. Min Act: -0.1700

Data Index: 1576511 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7533. Min Act: -0.1700

Data Index: 444561 (Open Web Text)

Max Activating Token Index: 984

Text #6

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7972. Min Act: -0.1700

Data Index: 7996171 (Open Web Text)

Max Activating Token Index: 111

Text #7

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7700. Min Act: -0.1700

Data Index: 8376713 (Open Web Text)

Max Activating Token Index: 475

Text #8

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7579. Min Act: -0.1700

Data Index: 2370481 (Open Web Text)

Max Activating Token Index: 684

Text #9

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7370. Min Act: -0.1700

Data Index: 5591229 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7309. Min Act: -0.1700

Data Index: 1629196 (Open Web Text)

Max Activating Token Index: 1006

Text #11

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7430. Min Act: -0.1700

Data Index: 4679659 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7420. Min Act: -0.1700

Data Index: 2365793 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7356. Min Act: -0.1700

Data Index: 1657652 (Open Web Text)

Max Activating Token Index: 390

Text #14

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7251. Min Act: -0.1700

Data Index: 645578 (Open Web Text)

Max Activating Token Index: 592

Text #15

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7463. Min Act: -0.1700

Data Index: 6203126 (Open Web Text)

Max Activating Token Index: 855

Text #16

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7541. Min Act: -0.1700

Data Index: 3758782 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7229. Min Act: -0.1700

Data Index: 4891923 (Open Web Text)

Max Activating Token Index: 643

Text #18

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7354. Min Act: -0.1700

Data Index: 6483460 (Open Web Text)

Max Activating Token Index: 780

Text #19

Max Range: 4.8759. Min Range: -4.8759

Max Act: 4.7263. Min Act: -0.1700

Data Index: 1516715 (Open Web Text)

Max Activating Token Index: 298