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

Dataset: Open Web Text

Neuron 2482 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: 5.0467. Min Range: -5.0467

Max Act: 5.0467. Min Act: -0.1700

Data Index: 3247111 (Open Web Text)

Max Activating Token Index: 754

Text #1

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.8757. Min Act: -0.1700

Data Index: 6923243 (Open Web Text)

Max Activating Token Index: 782

Text #2

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.8620. Min Act: -0.1700

Data Index: 1646063 (Open Web Text)

Max Activating Token Index: 847

Text #3

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.7169. Min Act: -0.1700

Data Index: 8720497 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.6696. Min Act: -0.1700

Data Index: 8354764 (Open Web Text)

Max Activating Token Index: 345

Text #5

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.6689. Min Act: -0.1700

Data Index: 8334153 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.6406. Min Act: -0.1700

Data Index: 725916 (Open Web Text)

Max Activating Token Index: 725

Text #7

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.6380. Min Act: -0.1700

Data Index: 8667842 (Open Web Text)

Max Activating Token Index: 318

Text #8

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.6266. Min Act: -0.1700

Data Index: 3166980 (Open Web Text)

Max Activating Token Index: 643

Text #9

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.5928. Min Act: -0.1700

Data Index: 6095587 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.6156. Min Act: -0.1700

Data Index: 8318209 (Open Web Text)

Max Activating Token Index: 324

Text #11

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.5712. Min Act: -0.1700

Data Index: 7723792 (Open Web Text)

Max Activating Token Index: 168

Text #12

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.5978. Min Act: -0.1700

Data Index: 6893318 (Open Web Text)

Max Activating Token Index: 322

Text #13

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.5387. Min Act: -0.1700

Data Index: 685171 (Open Web Text)

Max Activating Token Index: 944

Text #14

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.5517. Min Act: -0.1700

Data Index: 1910736 (Open Web Text)

Max Activating Token Index: 65

Text #15

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.5284. Min Act: -0.1700

Data Index: 8151551 (Open Web Text)

Max Activating Token Index: 646

Text #16

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.5241. Min Act: -0.1700

Data Index: 3817683 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.4859. Min Act: -0.1700

Data Index: 6591004 (Open Web Text)

Max Activating Token Index: 219

Text #18

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.5280. Min Act: -0.1700

Data Index: 5494076 (Open Web Text)

Max Activating Token Index: 599

Text #19

Max Range: 5.0467. Min Range: -5.0467

Max Act: 4.5134. Min Act: -0.1700

Data Index: 6918551 (Open Web Text)

Max Activating Token Index: 285