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

Dataset: Open Web Text

Neuron 2200 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: 3.9202. Min Range: -3.9202

Max Act: 3.9136. Min Act: -0.1700

Data Index: 3182559 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.9202. Min Act: -0.1700

Data Index: 4017169 (Open Web Text)

Max Activating Token Index: 718

Text #2

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.8633. Min Act: -0.1700

Data Index: 2538868 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.8746. Min Act: -0.1700

Data Index: 1479716 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.8497. Min Act: -0.1700

Data Index: 1645081 (Open Web Text)

Max Activating Token Index: 331

Text #5

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.8359. Min Act: -0.1700

Data Index: 187050 (Open Web Text)

Max Activating Token Index: 477

Text #6

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.8486. Min Act: -0.1700

Data Index: 7795193 (Open Web Text)

Max Activating Token Index: 254

Text #7

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7899. Min Act: -0.1700

Data Index: 8693901 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7974. Min Act: -0.1700

Data Index: 1960165 (Open Web Text)

Max Activating Token Index: 960

Text #9

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7747. Min Act: -0.1700

Data Index: 7495519 (Open Web Text)

Max Activating Token Index: 301

Text #10

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7740. Min Act: -0.1700

Data Index: 6259641 (Open Web Text)

Max Activating Token Index: 712

Text #11

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7593. Min Act: -0.1700

Data Index: 1374111 (Open Web Text)

Max Activating Token Index: 485

Text #12

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7889. Min Act: -0.1700

Data Index: 4544867 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7877. Min Act: -0.1700

Data Index: 5008633 (Open Web Text)

Max Activating Token Index: 506

Text #14

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7690. Min Act: -0.1700

Data Index: 2674440 (Open Web Text)

Max Activating Token Index: 188

Text #15

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7563. Min Act: -0.1700

Data Index: 5161340 (Open Web Text)

Max Activating Token Index: 478

Text #16

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7548. Min Act: -0.1700

Data Index: 408300 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7943. Min Act: -0.1700

Data Index: 5369759 (Open Web Text)

Max Activating Token Index: 577

Text #18

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7861. Min Act: -0.1700

Data Index: 1565055 (Open Web Text)

Max Activating Token Index: 934

Text #19

Max Range: 3.9202. Min Range: -3.9202

Max Act: 3.7483. Min Act: -0.1700

Data Index: 5674475 (Open Web Text)

Max Activating Token Index: 139