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

Dataset: Open Web Text

Neuron 1275 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: 4.0048. Min Range: -4.0048

Max Act: 3.9979. Min Act: -0.1700

Data Index: 6327299 (Open Web Text)

Max Activating Token Index: 540

Text #1

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9875. Min Act: -0.1700

Data Index: 7063394 (Open Web Text)

Max Activating Token Index: 551

Text #2

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9317. Min Act: -0.1700

Data Index: 5955890 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9623. Min Act: -0.1700

Data Index: 3459808 (Open Web Text)

Max Activating Token Index: 158

Text #4

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9759. Min Act: -0.1700

Data Index: 3549674 (Open Web Text)

Max Activating Token Index: 548

Text #5

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9574. Min Act: -0.1700

Data Index: 3636368 (Open Web Text)

Max Activating Token Index: 180

Text #6

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9370. Min Act: -0.1700

Data Index: 5380328 (Open Web Text)

Max Activating Token Index: 993

Text #7

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9742. Min Act: -0.1700

Data Index: 2488640 (Open Web Text)

Max Activating Token Index: 645

Text #8

Max Range: 4.0048. Min Range: -4.0048

Max Act: 4.0048. Min Act: -0.1700

Data Index: 6824871 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9489. Min Act: -0.1700

Data Index: 109922 (Open Web Text)

Max Activating Token Index: 523

Text #10

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9513. Min Act: -0.1700

Data Index: 2430198 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9329. Min Act: -0.1700

Data Index: 5509753 (Open Web Text)

Max Activating Token Index: 1017

Text #12

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9755. Min Act: -0.1700

Data Index: 5857713 (Open Web Text)

Max Activating Token Index: 493

Text #13

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9055. Min Act: -0.1700

Data Index: 2769797 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9270. Min Act: -0.1700

Data Index: 986999 (Open Web Text)

Max Activating Token Index: 374

Text #15

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9124. Min Act: -0.1700

Data Index: 8594809 (Open Web Text)

Max Activating Token Index: 418

Text #16

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.8825. Min Act: -0.1700

Data Index: 6359562 (Open Web Text)

Max Activating Token Index: 369

Text #17

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.9281. Min Act: -0.1700

Data Index: 1408258 (Open Web Text)

Max Activating Token Index: 285

Text #18

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.8684. Min Act: -0.1700

Data Index: 916918 (Open Web Text)

Max Activating Token Index: 250

Text #19

Max Range: 4.0048. Min Range: -4.0048

Max Act: 3.8356. Min Act: -0.1700

Data Index: 2737572 (Open Web Text)

Max Activating Token Index: 597