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

Dataset: Open Web Text

Neuron 821 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: 1.8903. Min Range: -1.8903

Max Act: 1.8903. Min Act: -0.1700

Data Index: 4616034 (Open Web Text)

Max Activating Token Index: 652

Text #1

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8868. Min Act: -0.1700

Data Index: 6350069 (Open Web Text)

Max Activating Token Index: 707

Text #2

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8451. Min Act: -0.1700

Data Index: 5360072 (Open Web Text)

Max Activating Token Index: 825

Text #3

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8384. Min Act: -0.1700

Data Index: 2015071 (Open Web Text)

Max Activating Token Index: 90

Text #4

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8305. Min Act: -0.1700

Data Index: 290373 (Open Web Text)

Max Activating Token Index: 285

Text #5

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.8016. Min Act: -0.1700

Data Index: 6600779 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7861. Min Act: -0.1700

Data Index: 3613728 (Open Web Text)

Max Activating Token Index: 401

Text #7

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7748. Min Act: -0.1700

Data Index: 5119914 (Open Web Text)

Max Activating Token Index: 712

Text #8

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7670. Min Act: -0.1700

Data Index: 4525892 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7655. Min Act: -0.1700

Data Index: 4273893 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7548. Min Act: -0.1700

Data Index: 4400666 (Open Web Text)

Max Activating Token Index: 389

Text #11

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7701. Min Act: -0.1700

Data Index: 3810730 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7604. Min Act: -0.1700

Data Index: 5529463 (Open Web Text)

Max Activating Token Index: 660

Text #13

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7559. Min Act: -0.1700

Data Index: 5614252 (Open Web Text)

Max Activating Token Index: 724

Text #14

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7482. Min Act: -0.1700

Data Index: 769397 (Open Web Text)

Max Activating Token Index: 115

Text #15

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7477. Min Act: -0.1700

Data Index: 4890476 (Open Web Text)

Max Activating Token Index: 645

Text #16

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7380. Min Act: -0.1700

Data Index: 7728958 (Open Web Text)

Max Activating Token Index: 125

Text #17

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7368. Min Act: -0.1700

Data Index: 6816935 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7377. Min Act: -0.1700

Data Index: 3409877 (Open Web Text)

Max Activating Token Index: 428

Text #19

Max Range: 1.8903. Min Range: -1.8903

Max Act: 1.7314. Min Act: -0.1700

Data Index: 5830591 (Open Web Text)

Max Activating Token Index: 440