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

Dataset: Open Web Text

Neuron 2593 in Layer 4

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: 3.8759. Min Range: -3.8759

Max Act: 3.8663. Min Act: -0.1700

Data Index: 7438380 (Open Web Text)

Max Activating Token Index: 248

Text #1

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8759. Min Act: -0.1700

Data Index: 753117 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7468. Min Act: -0.1700

Data Index: 6600308 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7082. Min Act: -0.1700

Data Index: 5275939 (Open Web Text)

Max Activating Token Index: 726

Text #4

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7200. Min Act: -0.1700

Data Index: 1836414 (Open Web Text)

Max Activating Token Index: 957

Text #5

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6816. Min Act: -0.1700

Data Index: 4683330 (Open Web Text)

Max Activating Token Index: 121

Text #6

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1618210 (Open Web Text)

Max Activating Token Index: 779

Text #7

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6505. Min Act: -0.1700

Data Index: 7688751 (Open Web Text)

Max Activating Token Index: 289

Text #8

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6416. Min Act: -0.1700

Data Index: 8700573 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6307. Min Act: -0.1700

Data Index: 2468249 (Open Web Text)

Max Activating Token Index: 764

Text #10

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6301. Min Act: -0.1700

Data Index: 2713154 (Open Web Text)

Max Activating Token Index: 797

Text #11

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.5882. Min Act: -0.1700

Data Index: 3957246 (Open Web Text)

Max Activating Token Index: 222

Text #12

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6219. Min Act: -0.1700

Data Index: 7308431 (Open Web Text)

Max Activating Token Index: 147

Text #13

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.5803. Min Act: -0.1700

Data Index: 3980223 (Open Web Text)

Max Activating Token Index: 590

Text #14

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.5877. Min Act: -0.1700

Data Index: 4603443 (Open Web Text)

Max Activating Token Index: 332

Text #15

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.5602. Min Act: -0.1700

Data Index: 8504767 (Open Web Text)

Max Activating Token Index: 917

Text #16

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.5568. Min Act: -0.1700

Data Index: 3501057 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.5550. Min Act: -0.1700

Data Index: 5462506 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.5537. Min Act: -0.1700

Data Index: 2261666 (Open Web Text)

Max Activating Token Index: 780

Text #19

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.5612. Min Act: -0.1700

Data Index: 1781459 (Open Web Text)

Max Activating Token Index: 73