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

Dataset: Open Web Text

Neuron 781 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: 1.3223. Min Range: -1.3223

Max Act: 1.3223. Min Act: -0.1700

Data Index: 7823299 (Open Web Text)

Max Activating Token Index: 715

Text #1

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.3150. Min Act: -0.1700

Data Index: 5918195 (Open Web Text)

Max Activating Token Index: 790

Text #2

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.3034. Min Act: -0.1700

Data Index: 7551456 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.3125. Min Act: -0.1700

Data Index: 484752 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2952. Min Act: -0.1700

Data Index: 3388453 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2952. Min Act: -0.1695

Data Index: 352087 (Open Web Text)

Max Activating Token Index: 664

Text #6

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2967. Min Act: -0.1700

Data Index: 6325653 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2811. Min Act: -0.1693

Data Index: 7574461 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2878. Min Act: -0.1700

Data Index: 8379419 (Open Web Text)

Max Activating Token Index: 363

Text #9

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2780. Min Act: -0.1700

Data Index: 6291956 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2612. Min Act: -0.1700

Data Index: 7180585 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2745. Min Act: -0.1700

Data Index: 3176041 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2892. Min Act: -0.1700

Data Index: 6510004 (Open Web Text)

Max Activating Token Index: 587

Text #13

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2757. Min Act: -0.1700

Data Index: 44023 (Open Web Text)

Max Activating Token Index: 93

Text #14

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2847. Min Act: -0.1700

Data Index: 3009349 (Open Web Text)

Max Activating Token Index: 799

Text #15

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2647. Min Act: -0.1700

Data Index: 3105508 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2694. Min Act: -0.1700

Data Index: 1622887 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2791. Min Act: -0.1700

Data Index: 4819594 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2692. Min Act: -0.1700

Data Index: 4693127 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 1.3223. Min Range: -1.3223

Max Act: 1.2572. Min Act: -0.1700

Data Index: 6071402 (Open Web Text)

Max Activating Token Index: 796