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

Dataset: Open Web Text

Neuron 325 in Layer 1

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: 1.5659. Min Range: -1.5659

Max Act: 1.5659. Min Act: -0.1700

Data Index: 7791132 (Open Web Text)

Max Activating Token Index: 699

Text #1

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.5445. Min Act: -0.1700

Data Index: 2517665 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.5099. Min Act: -0.1700

Data Index: 500532 (Open Web Text)

Max Activating Token Index: 862

Text #3

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.5153. Min Act: -0.1699

Data Index: 4757563 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.5035. Min Act: -0.1700

Data Index: 7993281 (Open Web Text)

Max Activating Token Index: 644

Text #5

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4889. Min Act: -0.1700

Data Index: 4075616 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4840. Min Act: -0.1695

Data Index: 7027008 (Open Web Text)

Max Activating Token Index: 670

Text #7

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4865. Min Act: -0.1700

Data Index: 3967850 (Open Web Text)

Max Activating Token Index: 306

Text #8

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4766. Min Act: -0.1700

Data Index: 3842488 (Open Web Text)

Max Activating Token Index: 771

Text #9

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4817. Min Act: -0.1695

Data Index: 4360214 (Open Web Text)

Max Activating Token Index: 183

Text #10

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4882. Min Act: -0.1698

Data Index: 8538878 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4762. Min Act: -0.1700

Data Index: 2741032 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4806. Min Act: -0.1700

Data Index: 605535 (Open Web Text)

Max Activating Token Index: 205

Text #13

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4734. Min Act: -0.1700

Data Index: 1617665 (Open Web Text)

Max Activating Token Index: 552

Text #14

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4798. Min Act: -0.1700

Data Index: 1061493 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4751. Min Act: -0.1683

Data Index: 7027009 (Open Web Text)

Max Activating Token Index: 271

Text #16

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4691. Min Act: -0.1700

Data Index: 3836224 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4635. Min Act: -0.1700

Data Index: 1074475 (Open Web Text)

Max Activating Token Index: 26

Text #18

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4725. Min Act: -0.1700

Data Index: 6007906 (Open Web Text)

Max Activating Token Index: 515

Text #19

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4618. Min Act: -0.1695

Data Index: 2912456 (Open Web Text)

Max Activating Token Index: 622