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

Dataset: Open Web Text

Neuron 48 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: 1.7615. Min Range: -1.7615

Max Act: 1.7615. Min Act: -0.1696

Data Index: 5871026 (Open Web Text)

Max Activating Token Index: 124

Text #1

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7606. Min Act: -0.1700

Data Index: 3206209 (Open Web Text)

Max Activating Token Index: 555

Text #2

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6804. Min Act: -0.1700

Data Index: 2856645 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6919. Min Act: -0.1700

Data Index: 5196704 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6854. Min Act: -0.1700

Data Index: 3942155 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6602. Min Act: -0.1700

Data Index: 8559171 (Open Web Text)

Max Activating Token Index: 281

Text #6

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6679. Min Act: -0.1700

Data Index: 6627388 (Open Web Text)

Max Activating Token Index: 829

Text #7

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6607. Min Act: -0.1700

Data Index: 8628307 (Open Web Text)

Max Activating Token Index: 820

Text #8

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6612. Min Act: -0.1700

Data Index: 1332033 (Open Web Text)

Max Activating Token Index: 846

Text #9

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6462. Min Act: -0.1700

Data Index: 2000703 (Open Web Text)

Max Activating Token Index: 940

Text #10

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6353. Min Act: -0.1700

Data Index: 329282 (Open Web Text)

Max Activating Token Index: 697

Text #11

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6402. Min Act: -0.1700

Data Index: 6477782 (Open Web Text)

Max Activating Token Index: 160

Text #12

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6356. Min Act: -0.1700

Data Index: 2905354 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6234. Min Act: -0.1700

Data Index: 410804 (Open Web Text)

Max Activating Token Index: 824

Text #14

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6224. Min Act: -0.1700

Data Index: 4783894 (Open Web Text)

Max Activating Token Index: 964

Text #15

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6149. Min Act: -0.1700

Data Index: 4942534 (Open Web Text)

Max Activating Token Index: 769

Text #16

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6188. Min Act: -0.1700

Data Index: 6538213 (Open Web Text)

Max Activating Token Index: 274

Text #17

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6104. Min Act: -0.1700

Data Index: 2862758 (Open Web Text)

Max Activating Token Index: 410

Text #18

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6085. Min Act: -0.1700

Data Index: 7331613 (Open Web Text)

Max Activating Token Index: 776

Text #19

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6104. Min Act: -0.1700

Data Index: 3626465 (Open Web Text)

Max Activating Token Index: 1022