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

Dataset: Open Web Text

Neuron 1489 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: 1.3470. Min Range: -1.3470

Max Act: 1.3470. Min Act: -0.1700

Data Index: 1927592 (Open Web Text)

Max Activating Token Index: 508

Text #1

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2911. Min Act: -0.1691

Data Index: 7358575 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2923. Min Act: -0.1657

Data Index: 8035127 (Open Web Text)

Max Activating Token Index: 386

Text #3

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2904. Min Act: -0.1697

Data Index: 2563307 (Open Web Text)

Max Activating Token Index: 535

Text #4

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2876. Min Act: -0.1662

Data Index: 5463045 (Open Web Text)

Max Activating Token Index: 656

Text #5

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2872. Min Act: -0.1700

Data Index: 7809507 (Open Web Text)

Max Activating Token Index: 946

Text #6

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2732. Min Act: -0.1697

Data Index: 3337438 (Open Web Text)

Max Activating Token Index: 663

Text #7

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2786. Min Act: -0.1661

Data Index: 1101471 (Open Web Text)

Max Activating Token Index: 598

Text #8

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2682. Min Act: -0.1696

Data Index: 1886607 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2601. Min Act: -0.1700

Data Index: 6308100 (Open Web Text)

Max Activating Token Index: 497

Text #10

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2655. Min Act: -0.1676

Data Index: 6287690 (Open Web Text)

Max Activating Token Index: 988

Text #11

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2703. Min Act: -0.1694

Data Index: 8172701 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2670. Min Act: -0.1692

Data Index: 7328408 (Open Web Text)

Max Activating Token Index: 628

Text #13

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2626. Min Act: -0.1697

Data Index: 5883953 (Open Web Text)

Max Activating Token Index: 591

Text #14

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2714. Min Act: -0.1697

Data Index: 2278796 (Open Web Text)

Max Activating Token Index: 470

Text #15

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2615. Min Act: -0.1674

Data Index: 5516332 (Open Web Text)

Max Activating Token Index: 610

Text #16

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2610. Min Act: -0.1691

Data Index: 4358026 (Open Web Text)

Max Activating Token Index: 553

Text #17

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2562. Min Act: -0.1700

Data Index: 2285163 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2560. Min Act: -0.1532

Data Index: 4957591 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.2532. Min Act: -0.1700

Data Index: 699820 (Open Web Text)

Max Activating Token Index: 660