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

Dataset: Open Web Text

Neuron 748 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: 3.7299. Min Range: -3.7299

Max Act: 3.7299. Min Act: -0.1700

Data Index: 2468583 (Open Web Text)

Max Activating Token Index: 485

Text #1

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.9948. Min Act: -0.1700

Data Index: 7386033 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.9447. Min Act: -0.1700

Data Index: 3174809 (Open Web Text)

Max Activating Token Index: 788

Text #3

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.8064. Min Act: -0.1700

Data Index: 3783110 (Open Web Text)

Max Activating Token Index: 424

Text #4

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.8627. Min Act: -0.1700

Data Index: 8236138 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.8304. Min Act: -0.1698

Data Index: 6556336 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.7859. Min Act: -0.1699

Data Index: 7520046 (Open Web Text)

Max Activating Token Index: 333

Text #7

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.7877. Min Act: -0.1700

Data Index: 6670218 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.7871. Min Act: -0.1700

Data Index: 8807689 (Open Web Text)

Max Activating Token Index: 812

Text #9

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.7723. Min Act: -0.1700

Data Index: 7008775 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.7173. Min Act: -0.1700

Data Index: 4361005 (Open Web Text)

Max Activating Token Index: 339

Text #11

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.6901. Min Act: -0.1700

Data Index: 1981883 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.6851. Min Act: -0.1700

Data Index: 5202414 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.6782. Min Act: -0.1700

Data Index: 3982142 (Open Web Text)

Max Activating Token Index: 851

Text #14

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.6161. Min Act: -0.1699

Data Index: 4332478 (Open Web Text)

Max Activating Token Index: 121

Text #15

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.6491. Min Act: -0.1700

Data Index: 8764025 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.5995. Min Act: -0.1700

Data Index: 1346192 (Open Web Text)

Max Activating Token Index: 973

Text #17

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.5768. Min Act: -0.1700

Data Index: 4405603 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.5814. Min Act: -0.1700

Data Index: 2041038 (Open Web Text)

Max Activating Token Index: 80

Text #19

Max Range: 3.7299. Min Range: -3.7299

Max Act: 2.5544. Min Act: -0.1700

Data Index: 4155307 (Open Web Text)

Max Activating Token Index: 937