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

Dataset: Open Web Text

Neuron 1021 in Layer 2

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: 1.8227. Min Range: -1.8227

Max Act: 1.8227. Min Act: -0.1700

Data Index: 1220476 (Open Web Text)

Max Activating Token Index: 108

Text #1

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7988. Min Act: -0.1700

Data Index: 3008528 (Open Web Text)

Max Activating Token Index: 634

Text #2

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7817. Min Act: -0.1700

Data Index: 5540986 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7633. Min Act: -0.1700

Data Index: 3328291 (Open Web Text)

Max Activating Token Index: 374

Text #4

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7522. Min Act: -0.1700

Data Index: 3244265 (Open Web Text)

Max Activating Token Index: 601

Text #5

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7789. Min Act: -0.1700

Data Index: 192666 (Open Web Text)

Max Activating Token Index: 733

Text #6

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7633. Min Act: -0.1700

Data Index: 1281791 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7459. Min Act: -0.1700

Data Index: 1910438 (Open Web Text)

Max Activating Token Index: 165

Text #8

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7366. Min Act: -0.1700

Data Index: 8233892 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7401. Min Act: -0.1700

Data Index: 7851644 (Open Web Text)

Max Activating Token Index: 799

Text #10

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7363. Min Act: -0.1700

Data Index: 1264746 (Open Web Text)

Max Activating Token Index: 487

Text #11

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7448. Min Act: -0.1700

Data Index: 49753 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7273. Min Act: -0.1700

Data Index: 3981609 (Open Web Text)

Max Activating Token Index: 494

Text #13

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7165. Min Act: -0.1700

Data Index: 3206427 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7268. Min Act: -0.1700

Data Index: 2170671 (Open Web Text)

Max Activating Token Index: 522

Text #15

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7064. Min Act: -0.1700

Data Index: 6941845 (Open Web Text)

Max Activating Token Index: 496

Text #16

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7346. Min Act: -0.1700

Data Index: 3800204 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.6954. Min Act: -0.1700

Data Index: 6324834 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.7053. Min Act: -0.1700

Data Index: 400932 (Open Web Text)

Max Activating Token Index: 682

Text #19

Max Range: 1.8227. Min Range: -1.8227

Max Act: 1.6970. Min Act: -0.1700

Data Index: 388034 (Open Web Text)

Max Activating Token Index: 1022