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

Dataset: Open Web Text

Neuron 2699 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: 4.0115. Min Range: -4.0115

Max Act: 4.0115. Min Act: -0.1700

Data Index: 1623772 (Open Web Text)

Max Activating Token Index: 479

Text #1

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.9980. Min Act: -0.1700

Data Index: 6904478 (Open Web Text)

Max Activating Token Index: 586

Text #2

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8903. Min Act: -0.1700

Data Index: 4671086 (Open Web Text)

Max Activating Token Index: 339

Text #3

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.9218. Min Act: -0.1700

Data Index: 1528425 (Open Web Text)

Max Activating Token Index: 377

Text #4

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8628. Min Act: -0.1700

Data Index: 6340006 (Open Web Text)

Max Activating Token Index: 563

Text #5

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8410. Min Act: -0.1700

Data Index: 8795410 (Open Web Text)

Max Activating Token Index: 987

Text #6

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8618. Min Act: -0.1700

Data Index: 4157336 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8536. Min Act: -0.1700

Data Index: 5426477 (Open Web Text)

Max Activating Token Index: 700

Text #8

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8482. Min Act: -0.1700

Data Index: 5572699 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8199. Min Act: -0.1700

Data Index: 3035997 (Open Web Text)

Max Activating Token Index: 763

Text #10

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8410. Min Act: -0.1700

Data Index: 373235 (Open Web Text)

Max Activating Token Index: 473

Text #11

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8320. Min Act: -0.1700

Data Index: 326220 (Open Web Text)

Max Activating Token Index: 332

Text #12

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8006. Min Act: -0.1700

Data Index: 2958733 (Open Web Text)

Max Activating Token Index: 503

Text #13

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.7867. Min Act: -0.1700

Data Index: 1476887 (Open Web Text)

Max Activating Token Index: 925

Text #14

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.7905. Min Act: -0.1700

Data Index: 412674 (Open Web Text)

Max Activating Token Index: 358

Text #15

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.7798. Min Act: -0.1700

Data Index: 3639292 (Open Web Text)

Max Activating Token Index: 90

Text #16

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.8191. Min Act: -0.1700

Data Index: 7256129 (Open Web Text)

Max Activating Token Index: 992

Text #17

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.7741. Min Act: -0.1700

Data Index: 3280660 (Open Web Text)

Max Activating Token Index: 677

Text #18

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.7811. Min Act: -0.1700

Data Index: 2169677 (Open Web Text)

Max Activating Token Index: 1011

Text #19

Max Range: 4.0115. Min Range: -4.0115

Max Act: 3.7836. Min Act: -0.1700

Data Index: 6589021 (Open Web Text)

Max Activating Token Index: 752