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

Dataset: Open Web Text

Neuron 2529 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: 4.0739. Min Range: -4.0739

Max Act: 4.0739. Min Act: -0.1700

Data Index: 2226032 (Open Web Text)

Max Activating Token Index: 772

Text #1

Max Range: 4.0739. Min Range: -4.0739

Max Act: 4.0114. Min Act: -0.1700

Data Index: 5239631 (Open Web Text)

Max Activating Token Index: 609

Text #2

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9508. Min Act: -0.1700

Data Index: 8017026 (Open Web Text)

Max Activating Token Index: 610

Text #3

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9722. Min Act: -0.1700

Data Index: 312256 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9612. Min Act: -0.1700

Data Index: 8198772 (Open Web Text)

Max Activating Token Index: 418

Text #5

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9683. Min Act: -0.1700

Data Index: 2762694 (Open Web Text)

Max Activating Token Index: 200

Text #6

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9939. Min Act: -0.1700

Data Index: 7960586 (Open Web Text)

Max Activating Token Index: 674

Text #7

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9785. Min Act: -0.1700

Data Index: 1156292 (Open Web Text)

Max Activating Token Index: 263

Text #8

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9849. Min Act: -0.1700

Data Index: 8198773 (Open Web Text)

Max Activating Token Index: 385

Text #9

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9229. Min Act: -0.1700

Data Index: 763994 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9551. Min Act: -0.1700

Data Index: 8391888 (Open Web Text)

Max Activating Token Index: 667

Text #11

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9695. Min Act: -0.1700

Data Index: 5829801 (Open Web Text)

Max Activating Token Index: 434

Text #12

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9402. Min Act: -0.1700

Data Index: 6381192 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.8829. Min Act: -0.1700

Data Index: 3729202 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9364. Min Act: -0.1700

Data Index: 5011175 (Open Web Text)

Max Activating Token Index: 556

Text #15

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9076. Min Act: -0.1700

Data Index: 2591638 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9053. Min Act: -0.1700

Data Index: 1598923 (Open Web Text)

Max Activating Token Index: 27

Text #17

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.8690. Min Act: -0.1700

Data Index: 5818035 (Open Web Text)

Max Activating Token Index: 417

Text #18

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9049. Min Act: -0.1700

Data Index: 5824367 (Open Web Text)

Max Activating Token Index: 84

Text #19

Max Range: 4.0739. Min Range: -4.0739

Max Act: 3.9224. Min Act: -0.1700

Data Index: 3384775 (Open Web Text)

Max Activating Token Index: 553