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

Dataset: Open Web Text

Neuron 566 in Layer 2

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: 2.1443. Min Range: -2.1443

Max Act: 2.1443. Min Act: -0.1700

Data Index: 1957099 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.1392. Min Act: -0.1700

Data Index: 4625787 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.1381. Min Act: -0.1700

Data Index: 866959 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.1219. Min Act: -0.1700

Data Index: 1538343 (Open Web Text)

Max Activating Token Index: 497

Text #4

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0816. Min Act: -0.1700

Data Index: 6156903 (Open Web Text)

Max Activating Token Index: 149

Text #5

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0873. Min Act: -0.1700

Data Index: 3416368 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0774. Min Act: -0.1700

Data Index: 3648989 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0646. Min Act: -0.1700

Data Index: 6353755 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0788. Min Act: -0.1700

Data Index: 1599278 (Open Web Text)

Max Activating Token Index: 264

Text #9

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0794. Min Act: -0.1700

Data Index: 1351142 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0757. Min Act: -0.1700

Data Index: 4889866 (Open Web Text)

Max Activating Token Index: 220

Text #11

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0794. Min Act: -0.1700

Data Index: 5666963 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0630. Min Act: -0.1700

Data Index: 6815314 (Open Web Text)

Max Activating Token Index: 78

Text #13

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0753. Min Act: -0.1700

Data Index: 3729049 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0607. Min Act: -0.1700

Data Index: 4220998 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0685. Min Act: -0.1700

Data Index: 52207 (Open Web Text)

Max Activating Token Index: 380

Text #16

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0728. Min Act: -0.1700

Data Index: 7696995 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0523. Min Act: -0.1700

Data Index: 119382 (Open Web Text)

Max Activating Token Index: 130

Text #18

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0623. Min Act: -0.1700

Data Index: 7323218 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.1443. Min Range: -2.1443

Max Act: 2.0589. Min Act: -0.1700

Data Index: 1071459 (Open Web Text)

Max Activating Token Index: 741