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

Dataset: Open Web Text

Neuron 1866 in Layer 0

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: 1.3567. Min Range: -1.3567

Max Act: 1.3567. Min Act: -0.1681

Data Index: 7950245 (Open Web Text)

Max Activating Token Index: 980

Text #1

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3450. Min Act: -0.1351

Data Index: 3446582 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3280. Min Act: -0.1508

Data Index: 5361840 (Open Web Text)

Max Activating Token Index: 531

Text #3

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3407. Min Act: -0.1696

Data Index: 5912601 (Open Web Text)

Max Activating Token Index: 927

Text #4

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3302. Min Act: -0.1562

Data Index: 5948779 (Open Web Text)

Max Activating Token Index: 382

Text #5

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3263. Min Act: -0.1550

Data Index: 7752791 (Open Web Text)

Max Activating Token Index: 962

Text #6

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3284. Min Act: -0.1553

Data Index: 2513872 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2941. Min Act: -0.1640

Data Index: 8510570 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2904. Min Act: -0.1605

Data Index: 5651256 (Open Web Text)

Max Activating Token Index: 540

Text #9

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2915. Min Act: -0.1447

Data Index: 7215381 (Open Web Text)

Max Activating Token Index: 238

Text #10

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2885. Min Act: -0.1603

Data Index: 2350952 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2837. Min Act: -0.1351

Data Index: 3535868 (Open Web Text)

Max Activating Token Index: 629

Text #12

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2773. Min Act: -0.1642

Data Index: 2355617 (Open Web Text)

Max Activating Token Index: 652

Text #13

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2741. Min Act: -0.1512

Data Index: 1059519 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2749. Min Act: -0.1652

Data Index: 5908822 (Open Web Text)

Max Activating Token Index: 620

Text #15

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2724. Min Act: -0.1700

Data Index: 4366461 (Open Web Text)

Max Activating Token Index: 584

Text #16

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2755. Min Act: -0.1530

Data Index: 4591595 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2848. Min Act: -0.1670

Data Index: 1301519 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2709. Min Act: -0.1488

Data Index: 2193065 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2687. Min Act: -0.1397

Data Index: 4735216 (Open Web Text)

Max Activating Token Index: 418