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

Dataset: Open Web Text

Neuron 2360 in Layer 3

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: 3.9044. Min Range: -3.9044

Max Act: 3.9044. Min Act: -0.1700

Data Index: 135518 (Open Web Text)

Max Activating Token Index: 376

Text #1

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.9012. Min Act: -0.1700

Data Index: 1931693 (Open Web Text)

Max Activating Token Index: 956

Text #2

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.8023. Min Act: -0.1700

Data Index: 652410 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.6375. Min Act: -0.1700

Data Index: 7628159 (Open Web Text)

Max Activating Token Index: 207

Text #4

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.6192. Min Act: -0.1700

Data Index: 7885720 (Open Web Text)

Max Activating Token Index: 924

Text #5

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.6387. Min Act: -0.1700

Data Index: 4001639 (Open Web Text)

Max Activating Token Index: 95

Text #6

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.6810. Min Act: -0.1700

Data Index: 7257071 (Open Web Text)

Max Activating Token Index: 142

Text #7

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.6574. Min Act: -0.1700

Data Index: 3016274 (Open Web Text)

Max Activating Token Index: 367

Text #8

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.5878. Min Act: -0.1700

Data Index: 6071539 (Open Web Text)

Max Activating Token Index: 290

Text #9

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.6596. Min Act: -0.1700

Data Index: 2608097 (Open Web Text)

Max Activating Token Index: 1002

Text #10

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.5276. Min Act: -0.1700

Data Index: 603816 (Open Web Text)

Max Activating Token Index: 768

Text #11

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.5652. Min Act: -0.1700

Data Index: 1980995 (Open Web Text)

Max Activating Token Index: 119

Text #12

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.4506. Min Act: -0.1700

Data Index: 8636754 (Open Web Text)

Max Activating Token Index: 511

Text #13

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.5608. Min Act: -0.1700

Data Index: 1702126 (Open Web Text)

Max Activating Token Index: 732

Text #14

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.5443. Min Act: -0.1700

Data Index: 6978135 (Open Web Text)

Max Activating Token Index: 636

Text #15

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.5375. Min Act: -0.1699

Data Index: 7001914 (Open Web Text)

Max Activating Token Index: 287

Text #16

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.5353. Min Act: -0.1700

Data Index: 7639801 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.5808. Min Act: -0.1700

Data Index: 5072573 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.4783. Min Act: -0.1700

Data Index: 473465 (Open Web Text)

Max Activating Token Index: 303

Text #19

Max Range: 3.9044. Min Range: -3.9044

Max Act: 3.5656. Min Act: -0.1700

Data Index: 4795742 (Open Web Text)

Max Activating Token Index: 302