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

Dataset: Open Web Text

Neuron 233 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: 1.4500. Min Range: -1.4500

Max Act: 1.4500. Min Act: -0.1700

Data Index: 3963271 (Open Web Text)

Max Activating Token Index: 505

Text #1

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.4413. Min Act: -0.1700

Data Index: 3861232 (Open Web Text)

Max Activating Token Index: 606

Text #2

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.4350. Min Act: -0.1700

Data Index: 2085093 (Open Web Text)

Max Activating Token Index: 481

Text #3

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.4077. Min Act: -0.1700

Data Index: 1273299 (Open Web Text)

Max Activating Token Index: 831

Text #4

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3884. Min Act: -0.1700

Data Index: 2316325 (Open Web Text)

Max Activating Token Index: 980

Text #5

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3927. Min Act: -0.1690

Data Index: 2419552 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3849. Min Act: -0.1700

Data Index: 6369211 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3893. Min Act: -0.1700

Data Index: 4084196 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3749. Min Act: -0.1700

Data Index: 3291223 (Open Web Text)

Max Activating Token Index: 424

Text #9

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3701. Min Act: -0.1700

Data Index: 4547388 (Open Web Text)

Max Activating Token Index: 508

Text #10

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3659. Min Act: -0.1699

Data Index: 3227358 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3663. Min Act: -0.1700

Data Index: 508627 (Open Web Text)

Max Activating Token Index: 542

Text #12

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3612. Min Act: -0.1674

Data Index: 5838837 (Open Web Text)

Max Activating Token Index: 452

Text #13

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3572. Min Act: -0.1700

Data Index: 8041586 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3542. Min Act: -0.1690

Data Index: 6160375 (Open Web Text)

Max Activating Token Index: 683

Text #15

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3539. Min Act: -0.1700

Data Index: 5373717 (Open Web Text)

Max Activating Token Index: 640

Text #16

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3584. Min Act: -0.1697

Data Index: 8253707 (Open Web Text)

Max Activating Token Index: 425

Text #17

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3603. Min Act: -0.1696

Data Index: 280178 (Open Web Text)

Max Activating Token Index: 1010

Text #18

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3590. Min Act: -0.1700

Data Index: 8451343 (Open Web Text)

Max Activating Token Index: 554

Text #19

Max Range: 1.4500. Min Range: -1.4500

Max Act: 1.3624. Min Act: -0.1700

Data Index: 6672192 (Open Web Text)

Max Activating Token Index: 482