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

Dataset: Open Web Text

Neuron 1594 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: 4.5392. Min Range: -4.5392

Max Act: 4.5392. Min Act: -0.1700

Data Index: 825768 (Open Web Text)

Max Activating Token Index: 752

Text #1

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.4280. Min Act: -0.1700

Data Index: 3454532 (Open Web Text)

Max Activating Token Index: 647

Text #2

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.3485. Min Act: -0.1700

Data Index: 8790598 (Open Web Text)

Max Activating Token Index: 654

Text #3

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.3260. Min Act: -0.1700

Data Index: 811529 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.2653. Min Act: -0.1700

Data Index: 2713499 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.2490. Min Act: -0.1700

Data Index: 4696361 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.2239. Min Act: -0.1700

Data Index: 2561510 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.2081. Min Act: -0.1700

Data Index: 1695683 (Open Web Text)

Max Activating Token Index: 794

Text #8

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.2000. Min Act: -0.1700

Data Index: 1062010 (Open Web Text)

Max Activating Token Index: 780

Text #9

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.2139. Min Act: -0.1700

Data Index: 5061746 (Open Web Text)

Max Activating Token Index: 675

Text #10

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.1893. Min Act: -0.1700

Data Index: 7991613 (Open Web Text)

Max Activating Token Index: 262

Text #11

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.2220. Min Act: -0.1700

Data Index: 7346386 (Open Web Text)

Max Activating Token Index: 816

Text #12

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.2051. Min Act: -0.1700

Data Index: 2801336 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.2045. Min Act: -0.1700

Data Index: 2474033 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.1846. Min Act: -0.1700

Data Index: 6601054 (Open Web Text)

Max Activating Token Index: 543

Text #15

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.1807. Min Act: -0.1700

Data Index: 4438101 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.1185. Min Act: -0.1700

Data Index: 3753664 (Open Web Text)

Max Activating Token Index: 493

Text #17

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.1486. Min Act: -0.1700

Data Index: 3415577 (Open Web Text)

Max Activating Token Index: 289

Text #18

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.1516. Min Act: -0.1700

Data Index: 1187880 (Open Web Text)

Max Activating Token Index: 248

Text #19

Max Range: 4.5392. Min Range: -4.5392

Max Act: 4.1683. Min Act: -0.1700

Data Index: 4119983 (Open Web Text)

Max Activating Token Index: 673