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

Dataset: Open Web Text

Neuron 2993 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: 1.9646. Min Range: -1.9646

Max Act: 1.9646. Min Act: -0.1700

Data Index: 4991429 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8368. Min Act: -0.1700

Data Index: 7256075 (Open Web Text)

Max Activating Token Index: 918

Text #2

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8240. Min Act: -0.1699

Data Index: 823370 (Open Web Text)

Max Activating Token Index: 837

Text #3

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8222. Min Act: -0.1700

Data Index: 262571 (Open Web Text)

Max Activating Token Index: 837

Text #4

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8122. Min Act: -0.1700

Data Index: 4045717 (Open Web Text)

Max Activating Token Index: 781

Text #5

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7947. Min Act: -0.1700

Data Index: 2546938 (Open Web Text)

Max Activating Token Index: 120

Text #6

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7891. Min Act: -0.1700

Data Index: 4988883 (Open Web Text)

Max Activating Token Index: 729

Text #7

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7810. Min Act: -0.1700

Data Index: 6689415 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7817. Min Act: -0.1698

Data Index: 4699018 (Open Web Text)

Max Activating Token Index: 217

Text #9

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7696. Min Act: -0.1700

Data Index: 3132662 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7682. Min Act: -0.1700

Data Index: 8261980 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7793. Min Act: -0.1700

Data Index: 2180552 (Open Web Text)

Max Activating Token Index: 984

Text #12

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7711. Min Act: -0.1700

Data Index: 699105 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7602. Min Act: -0.1700

Data Index: 5027064 (Open Web Text)

Max Activating Token Index: 356

Text #14

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7593. Min Act: -0.1700

Data Index: 2799099 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7674. Min Act: -0.1700

Data Index: 4200192 (Open Web Text)

Max Activating Token Index: 103

Text #16

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7587. Min Act: -0.1700

Data Index: 6824453 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7484. Min Act: -0.1700

Data Index: 7332127 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7449. Min Act: -0.1700

Data Index: 5288965 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7631. Min Act: -0.1700

Data Index: 1877189 (Open Web Text)

Max Activating Token Index: 805