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

Dataset: Open Web Text

Neuron 2709 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: 2.3672. Min Range: -2.3672

Max Act: 2.3672. Min Act: -0.1700

Data Index: 5835763 (Open Web Text)

Max Activating Token Index: 180

Text #1

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.3470. Min Act: -0.1700

Data Index: 5835761 (Open Web Text)

Max Activating Token Index: 147

Text #2

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.3237. Min Act: -0.1627

Data Index: 6940812 (Open Web Text)

Max Activating Token Index: 744

Text #3

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2903. Min Act: -0.1699

Data Index: 5719588 (Open Web Text)

Max Activating Token Index: 415

Text #4

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.3053. Min Act: -0.1698

Data Index: 6940809 (Open Web Text)

Max Activating Token Index: 210

Text #5

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2935. Min Act: -0.1699

Data Index: 840463 (Open Web Text)

Max Activating Token Index: 361

Text #6

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2900. Min Act: -0.1700

Data Index: 2655861 (Open Web Text)

Max Activating Token Index: 283

Text #7

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2964. Min Act: -0.1700

Data Index: 2602449 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2787. Min Act: -0.1700

Data Index: 1073131 (Open Web Text)

Max Activating Token Index: 515

Text #9

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2807. Min Act: -0.1700

Data Index: 5196190 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2724. Min Act: -0.1700

Data Index: 8560821 (Open Web Text)

Max Activating Token Index: 97

Text #11

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2911. Min Act: -0.1700

Data Index: 7840421 (Open Web Text)

Max Activating Token Index: 255

Text #12

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2832. Min Act: -0.1683

Data Index: 6940800 (Open Web Text)

Max Activating Token Index: 990

Text #13

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2860. Min Act: -0.1700

Data Index: 4047441 (Open Web Text)

Max Activating Token Index: 260

Text #14

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2763. Min Act: -0.1670

Data Index: 6940797 (Open Web Text)

Max Activating Token Index: 313

Text #15

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2799. Min Act: -0.1700

Data Index: 6765498 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2786. Min Act: -0.1697

Data Index: 3898106 (Open Web Text)

Max Activating Token Index: 857

Text #17

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2754. Min Act: -0.1696

Data Index: 3796902 (Open Web Text)

Max Activating Token Index: 735

Text #18

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2634. Min Act: -0.1700

Data Index: 1759520 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 2.3672. Min Range: -2.3672

Max Act: 2.2615. Min Act: -0.1699

Data Index: 5196192 (Open Web Text)

Max Activating Token Index: 653