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

Dataset: Open Web Text

Neuron 2719 in Layer 4

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: 3.9479. Min Range: -3.9479

Max Act: 3.9479. Min Act: -0.1700

Data Index: 2632780 (Open Web Text)

Max Activating Token Index: 1000

Text #1

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.8443. Min Act: -0.1700

Data Index: 468179 (Open Web Text)

Max Activating Token Index: 391

Text #2

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.8518. Min Act: -0.1700

Data Index: 4634609 (Open Web Text)

Max Activating Token Index: 709

Text #3

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.8101. Min Act: -0.1700

Data Index: 7012386 (Open Web Text)

Max Activating Token Index: 718

Text #4

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.8050. Min Act: -0.1700

Data Index: 1771687 (Open Web Text)

Max Activating Token Index: 286

Text #5

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.8027. Min Act: -0.1700

Data Index: 7473497 (Open Web Text)

Max Activating Token Index: 842

Text #6

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.8100. Min Act: -0.1700

Data Index: 6480096 (Open Web Text)

Max Activating Token Index: 742

Text #7

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7780. Min Act: -0.1700

Data Index: 5532663 (Open Web Text)

Max Activating Token Index: 339

Text #8

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7587. Min Act: -0.1700

Data Index: 7609721 (Open Web Text)

Max Activating Token Index: 295

Text #9

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7626. Min Act: -0.1700

Data Index: 2055957 (Open Web Text)

Max Activating Token Index: 288

Text #10

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7789. Min Act: -0.1700

Data Index: 2643679 (Open Web Text)

Max Activating Token Index: 492

Text #11

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7512. Min Act: -0.1700

Data Index: 7811643 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7659. Min Act: -0.1700

Data Index: 2458794 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7489. Min Act: -0.1700

Data Index: 1778506 (Open Web Text)

Max Activating Token Index: 963

Text #14

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7606. Min Act: -0.1700

Data Index: 4309323 (Open Web Text)

Max Activating Token Index: 912

Text #15

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7596. Min Act: -0.1700

Data Index: 2835524 (Open Web Text)

Max Activating Token Index: 587

Text #16

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7241. Min Act: -0.1700

Data Index: 5594111 (Open Web Text)

Max Activating Token Index: 199

Text #17

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7093. Min Act: -0.1700

Data Index: 5644389 (Open Web Text)

Max Activating Token Index: 654

Text #18

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7686. Min Act: -0.1700

Data Index: 36666 (Open Web Text)

Max Activating Token Index: 805

Text #19

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7210. Min Act: -0.1700

Data Index: 8580090 (Open Web Text)

Max Activating Token Index: 558