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

Dataset: Open Web Text

Neuron 3038 in Layer 6

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: 3.0531. Min Range: -3.0531

Max Act: 3.0531. Min Act: -0.1700

Data Index: 3087233 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 3.0531. Min Range: -3.0531

Max Act: 3.0522. Min Act: -0.1700

Data Index: 3514550 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 3.0531. Min Range: -3.0531

Max Act: 3.0403. Min Act: -0.1700

Data Index: 6359764 (Open Web Text)

Max Activating Token Index: 146

Text #3

Max Range: 3.0531. Min Range: -3.0531

Max Act: 3.0273. Min Act: -0.1700

Data Index: 3852568 (Open Web Text)

Max Activating Token Index: 882

Text #4

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.9446. Min Act: -0.1700

Data Index: 189801 (Open Web Text)

Max Activating Token Index: 145

Text #5

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.9601. Min Act: -0.1700

Data Index: 3503411 (Open Web Text)

Max Activating Token Index: 228

Text #6

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.9161. Min Act: -0.1700

Data Index: 3826394 (Open Web Text)

Max Activating Token Index: 928

Text #7

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8875. Min Act: -0.1700

Data Index: 2475605 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8725. Min Act: -0.1700

Data Index: 2079899 (Open Web Text)

Max Activating Token Index: 393

Text #9

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8714. Min Act: -0.1700

Data Index: 3216802 (Open Web Text)

Max Activating Token Index: 784

Text #10

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8711. Min Act: -0.1700

Data Index: 4126501 (Open Web Text)

Max Activating Token Index: 583

Text #11

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8794. Min Act: -0.1700

Data Index: 2901953 (Open Web Text)

Max Activating Token Index: 858

Text #12

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8649. Min Act: -0.1700

Data Index: 151575 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8627. Min Act: -0.1700

Data Index: 1212909 (Open Web Text)

Max Activating Token Index: 329

Text #14

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8650. Min Act: -0.1700

Data Index: 7004800 (Open Web Text)

Max Activating Token Index: 578

Text #15

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8395. Min Act: -0.1700

Data Index: 3279227 (Open Web Text)

Max Activating Token Index: 688

Text #16

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8196. Min Act: -0.1700

Data Index: 3845240 (Open Web Text)

Max Activating Token Index: 995

Text #17

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8650. Min Act: -0.1700

Data Index: 2589025 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8393. Min Act: -0.1700

Data Index: 3102743 (Open Web Text)

Max Activating Token Index: 827

Text #19

Max Range: 3.0531. Min Range: -3.0531

Max Act: 2.8401. Min Act: -0.1700

Data Index: 2300375 (Open Web Text)

Max Activating Token Index: 708