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

Dataset: Open Web Text

Neuron 933 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: 1.2960. Min Range: -1.2960

Max Act: 1.2960. Min Act: -0.0584

Data Index: 8614476 (Open Web Text)

Max Activating Token Index: 623

Text #1

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2936. Min Act: -0.1158

Data Index: 6248008 (Open Web Text)

Max Activating Token Index: 632

Text #2

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2882. Min Act: -0.1425

Data Index: 6461958 (Open Web Text)

Max Activating Token Index: 715

Text #3

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2761. Min Act: -0.1302

Data Index: 4700720 (Open Web Text)

Max Activating Token Index: 672

Text #4

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2807. Min Act: -0.0706

Data Index: 303717 (Open Web Text)

Max Activating Token Index: 679

Text #5

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2811. Min Act: -0.0996

Data Index: 4765503 (Open Web Text)

Max Activating Token Index: 616

Text #6

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2760. Min Act: -0.0716

Data Index: 8143085 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2756. Min Act: -0.1061

Data Index: 1175971 (Open Web Text)

Max Activating Token Index: 690

Text #8

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2741. Min Act: -0.1479

Data Index: 77007 (Open Web Text)

Max Activating Token Index: 687

Text #9

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2770. Min Act: -0.1171

Data Index: 5591269 (Open Web Text)

Max Activating Token Index: 638

Text #10

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2802. Min Act: -0.1302

Data Index: 4035105 (Open Web Text)

Max Activating Token Index: 663

Text #11

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2750. Min Act: -0.1240

Data Index: 828628 (Open Web Text)

Max Activating Token Index: 634

Text #12

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2695. Min Act: -0.0804

Data Index: 7441662 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2761. Min Act: -0.0500

Data Index: 4329430 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2719. Min Act: -0.1187

Data Index: 6609382 (Open Web Text)

Max Activating Token Index: 414

Text #15

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2617. Min Act: -0.0477

Data Index: 1868727 (Open Web Text)

Max Activating Token Index: 674

Text #16

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2652. Min Act: -0.0957

Data Index: 6268095 (Open Web Text)

Max Activating Token Index: 624

Text #17

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2589. Min Act: -0.1302

Data Index: 3421744 (Open Web Text)

Max Activating Token Index: 667

Text #18

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2592. Min Act: -0.1536

Data Index: 3021953 (Open Web Text)

Max Activating Token Index: 620

Text #19

Max Range: 1.2960. Min Range: -1.2960

Max Act: 1.2659. Min Act: -0.1327

Data Index: 6691223 (Open Web Text)

Max Activating Token Index: 630