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

Dataset: Open Web Text

Neuron 782 in Layer 3

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: 3.9821. Min Range: -3.9821

Max Act: 3.9697. Min Act: -0.1700

Data Index: 8698042 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.9821. Min Act: -0.1700

Data Index: 1992965 (Open Web Text)

Max Activating Token Index: 399

Text #2

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.9008. Min Act: -0.1700

Data Index: 3961974 (Open Web Text)

Max Activating Token Index: 220

Text #3

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.9469. Min Act: -0.1700

Data Index: 542732 (Open Web Text)

Max Activating Token Index: 564

Text #4

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.8681. Min Act: -0.1700

Data Index: 8421970 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.8496. Min Act: -0.1700

Data Index: 4010849 (Open Web Text)

Max Activating Token Index: 1008

Text #6

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.8366. Min Act: -0.1700

Data Index: 3732201 (Open Web Text)

Max Activating Token Index: 549

Text #7

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.8205. Min Act: -0.1700

Data Index: 7320060 (Open Web Text)

Max Activating Token Index: 85

Text #8

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.8139. Min Act: -0.1700

Data Index: 8457372 (Open Web Text)

Max Activating Token Index: 596

Text #9

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7459. Min Act: -0.1700

Data Index: 8421971 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7847. Min Act: -0.1700

Data Index: 2545366 (Open Web Text)

Max Activating Token Index: 191

Text #11

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7688. Min Act: -0.1700

Data Index: 5132759 (Open Web Text)

Max Activating Token Index: 1017

Text #12

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7730. Min Act: -0.1700

Data Index: 1074574 (Open Web Text)

Max Activating Token Index: 98

Text #13

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7702. Min Act: -0.1700

Data Index: 7862438 (Open Web Text)

Max Activating Token Index: 945

Text #14

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7589. Min Act: -0.1700

Data Index: 8311780 (Open Web Text)

Max Activating Token Index: 157

Text #15

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7683. Min Act: -0.1700

Data Index: 6103577 (Open Web Text)

Max Activating Token Index: 193

Text #16

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7439. Min Act: -0.1700

Data Index: 3544928 (Open Web Text)

Max Activating Token Index: 728

Text #17

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7205. Min Act: -0.1700

Data Index: 1074576 (Open Web Text)

Max Activating Token Index: 425

Text #18

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.7128. Min Act: -0.1700

Data Index: 2533269 (Open Web Text)

Max Activating Token Index: 997

Text #19

Max Range: 3.9821. Min Range: -3.9821

Max Act: 3.6965. Min Act: -0.1700

Data Index: 2130854 (Open Web Text)

Max Activating Token Index: 350