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

Dataset: Open Web Text

Neuron 2560 in Layer 1

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: 1.7636. Min Range: -1.7636

Max Act: 1.7636. Min Act: -0.1700

Data Index: 6717589 (Open Web Text)

Max Activating Token Index: 614

Text #1

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.7489. Min Act: -0.1699

Data Index: 3187197 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.7289. Min Act: -0.1700

Data Index: 6848016 (Open Web Text)

Max Activating Token Index: 551

Text #3

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.7049. Min Act: -0.1700

Data Index: 8468302 (Open Web Text)

Max Activating Token Index: 240

Text #4

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6807. Min Act: -0.1700

Data Index: 3474849 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6734. Min Act: -0.1700

Data Index: 6914933 (Open Web Text)

Max Activating Token Index: 186

Text #6

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6620. Min Act: -0.1700

Data Index: 4730252 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6558. Min Act: -0.1700

Data Index: 1804971 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6526. Min Act: -0.1700

Data Index: 7952750 (Open Web Text)

Max Activating Token Index: 700

Text #9

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6555. Min Act: -0.1700

Data Index: 4749219 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6552. Min Act: -0.1698

Data Index: 3958722 (Open Web Text)

Max Activating Token Index: 93

Text #11

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6545. Min Act: -0.1700

Data Index: 8090509 (Open Web Text)

Max Activating Token Index: 234

Text #12

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6461. Min Act: -0.1693

Data Index: 8011675 (Open Web Text)

Max Activating Token Index: 706

Text #13

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6429. Min Act: -0.1700

Data Index: 4710083 (Open Web Text)

Max Activating Token Index: 672

Text #14

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6314. Min Act: -0.1700

Data Index: 5591380 (Open Web Text)

Max Activating Token Index: 278

Text #15

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6403. Min Act: -0.1700

Data Index: 840068 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6396. Min Act: -0.1700

Data Index: 26070 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6371. Min Act: -0.1700

Data Index: 1460385 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6397. Min Act: -0.1700

Data Index: 6018379 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 1.7636. Min Range: -1.7636

Max Act: 1.6272. Min Act: -0.1700

Data Index: 5859514 (Open Web Text)

Max Activating Token Index: 417