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

Dataset: Open Web Text

Neuron 1313 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: 4.5429. Min Range: -4.5429

Max Act: 4.5429. Min Act: -0.1700

Data Index: 7574306 (Open Web Text)

Max Activating Token Index: 502

Text #1

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.4875. Min Act: -0.1700

Data Index: 6084560 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.4379. Min Act: -0.1700

Data Index: 6765797 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.4057. Min Act: -0.1700

Data Index: 6765799 (Open Web Text)

Max Activating Token Index: 202

Text #4

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.3181. Min Act: -0.1700

Data Index: 6407090 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.3118. Min Act: -0.1700

Data Index: 5369885 (Open Web Text)

Max Activating Token Index: 643

Text #6

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.3079. Min Act: -0.1700

Data Index: 2806027 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2747. Min Act: -0.1700

Data Index: 4415806 (Open Web Text)

Max Activating Token Index: 730

Text #8

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.3130. Min Act: -0.1700

Data Index: 7273717 (Open Web Text)

Max Activating Token Index: 973

Text #9

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2833. Min Act: -0.1700

Data Index: 7937822 (Open Web Text)

Max Activating Token Index: 489

Text #10

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2462. Min Act: -0.1700

Data Index: 309519 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2539. Min Act: -0.1700

Data Index: 7516158 (Open Web Text)

Max Activating Token Index: 128

Text #12

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2479. Min Act: -0.1700

Data Index: 4084099 (Open Web Text)

Max Activating Token Index: 216

Text #13

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2442. Min Act: -0.1700

Data Index: 5419442 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2591. Min Act: -0.1700

Data Index: 2581995 (Open Web Text)

Max Activating Token Index: 478

Text #15

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2346. Min Act: -0.1700

Data Index: 2615263 (Open Web Text)

Max Activating Token Index: 698

Text #16

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2485. Min Act: -0.1700

Data Index: 8633700 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2137. Min Act: -0.1700

Data Index: 1141746 (Open Web Text)

Max Activating Token Index: 297

Text #18

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2397. Min Act: -0.1700

Data Index: 4120926 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 4.5429. Min Range: -4.5429

Max Act: 4.2191. Min Act: -0.1700

Data Index: 469486 (Open Web Text)

Max Activating Token Index: 592