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

Dataset: Open Web Text

Neuron 1204 in Layer 5

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: 4.3580. Min Range: -4.3580

Max Act: 4.3580. Min Act: -0.1700

Data Index: 7374559 (Open Web Text)

Max Activating Token Index: 460

Text #1

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.3111. Min Act: -0.1700

Data Index: 5710524 (Open Web Text)

Max Activating Token Index: 891

Text #2

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.2977. Min Act: -0.1700

Data Index: 6798606 (Open Web Text)

Max Activating Token Index: 778

Text #3

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.2423. Min Act: -0.1700

Data Index: 8261165 (Open Web Text)

Max Activating Token Index: 690

Text #4

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.2193. Min Act: -0.1700

Data Index: 2405928 (Open Web Text)

Max Activating Token Index: 647

Text #5

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.1548. Min Act: -0.1700

Data Index: 8585837 (Open Web Text)

Max Activating Token Index: 340

Text #6

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.0798. Min Act: -0.1700

Data Index: 3339465 (Open Web Text)

Max Activating Token Index: 836

Text #7

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.1020. Min Act: -0.1700

Data Index: 8274139 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.0694. Min Act: -0.1700

Data Index: 1009161 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.0073. Min Act: -0.1700

Data Index: 7467923 (Open Web Text)

Max Activating Token Index: 161

Text #10

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.0245. Min Act: -0.1700

Data Index: 1919904 (Open Web Text)

Max Activating Token Index: 525

Text #11

Max Range: 4.3580. Min Range: -4.3580

Max Act: 4.0195. Min Act: -0.1700

Data Index: 4618461 (Open Web Text)

Max Activating Token Index: 968

Text #12

Max Range: 4.3580. Min Range: -4.3580

Max Act: 3.9624. Min Act: -0.1700

Data Index: 6236769 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 4.3580. Min Range: -4.3580

Max Act: 3.9523. Min Act: -0.1700

Data Index: 1910222 (Open Web Text)

Max Activating Token Index: 600

Text #14

Max Range: 4.3580. Min Range: -4.3580

Max Act: 3.9891. Min Act: -0.1700

Data Index: 6955367 (Open Web Text)

Max Activating Token Index: 264

Text #15

Max Range: 4.3580. Min Range: -4.3580

Max Act: 3.9697. Min Act: -0.1700

Data Index: 7699339 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 4.3580. Min Range: -4.3580

Max Act: 3.9546. Min Act: -0.1700

Data Index: 3252376 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 4.3580. Min Range: -4.3580

Max Act: 3.9626. Min Act: -0.1700

Data Index: 6331601 (Open Web Text)

Max Activating Token Index: 750

Text #18

Max Range: 4.3580. Min Range: -4.3580

Max Act: 3.9284. Min Act: -0.1700

Data Index: 2950654 (Open Web Text)

Max Activating Token Index: 748

Text #19

Max Range: 4.3580. Min Range: -4.3580

Max Act: 3.9161. Min Act: -0.1700

Data Index: 7979930 (Open Web Text)

Max Activating Token Index: 52