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

Dataset: Open Web Text

Neuron 824 in Layer 0

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: 2.8334. Min Range: -2.8334

Max Act: 2.8334. Min Act: -0.1700

Data Index: 4800532 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.8232. Min Act: -0.1700

Data Index: 7829593 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.8113. Min Act: -0.1700

Data Index: 6985583 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.8043. Min Act: -0.1700

Data Index: 7830081 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.8011. Min Act: -0.1700

Data Index: 7448854 (Open Web Text)

Max Activating Token Index: 412

Text #5

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7771. Min Act: -0.1700

Data Index: 8097996 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7655. Min Act: -0.1700

Data Index: 2382800 (Open Web Text)

Max Activating Token Index: 387

Text #7

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7706. Min Act: -0.1700

Data Index: 65400 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7437. Min Act: -0.1700

Data Index: 5117479 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7559. Min Act: -0.1700

Data Index: 2528591 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7507. Min Act: -0.1700

Data Index: 7863556 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7533. Min Act: -0.1700

Data Index: 5907243 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7332. Min Act: -0.1700

Data Index: 4682653 (Open Web Text)

Max Activating Token Index: 853

Text #13

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7447. Min Act: -0.1700

Data Index: 8053760 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7107. Min Act: -0.1700

Data Index: 1904929 (Open Web Text)

Max Activating Token Index: 456

Text #15

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7235. Min Act: -0.1700

Data Index: 3894211 (Open Web Text)

Max Activating Token Index: 941

Text #16

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7274. Min Act: -0.1700

Data Index: 1366133 (Open Web Text)

Max Activating Token Index: 331

Text #17

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7195. Min Act: -0.1700

Data Index: 1000396 (Open Web Text)

Max Activating Token Index: 183

Text #18

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7153. Min Act: -0.1700

Data Index: 4699324 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.8334. Min Range: -2.8334

Max Act: 2.7166. Min Act: -0.1700

Data Index: 1192048 (Open Web Text)

Max Activating Token Index: 43