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

Dataset: Open Web Text

Neuron 1827 in Layer 0

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: 2.4994. Min Range: -2.4994

Max Act: 2.4716. Min Act: -0.1700

Data Index: 1849328 (Open Web Text)

Max Activating Token Index: 874

Text #1

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4419. Min Act: -0.1700

Data Index: 8106760 (Open Web Text)

Max Activating Token Index: 933

Text #2

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4994. Min Act: -0.1700

Data Index: 5362374 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4346. Min Act: -0.1700

Data Index: 7221938 (Open Web Text)

Max Activating Token Index: 885

Text #4

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4675. Min Act: -0.1700

Data Index: 6582637 (Open Web Text)

Max Activating Token Index: 673

Text #5

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4570. Min Act: -0.1700

Data Index: 3693175 (Open Web Text)

Max Activating Token Index: 877

Text #6

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4292. Min Act: -0.1700

Data Index: 8608908 (Open Web Text)

Max Activating Token Index: 823

Text #7

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4245. Min Act: -0.1700

Data Index: 5208300 (Open Web Text)

Max Activating Token Index: 673

Text #8

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4266. Min Act: -0.1700

Data Index: 374388 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.3903. Min Act: -0.1700

Data Index: 322413 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4012. Min Act: -0.1700

Data Index: 4836957 (Open Web Text)

Max Activating Token Index: 991

Text #11

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.3755. Min Act: -0.1700

Data Index: 7076796 (Open Web Text)

Max Activating Token Index: 934

Text #12

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.3518. Min Act: -0.1700

Data Index: 471263 (Open Web Text)

Max Activating Token Index: 994

Text #13

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.3613. Min Act: -0.1700

Data Index: 8254021 (Open Web Text)

Max Activating Token Index: 826

Text #14

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4037. Min Act: -0.1700

Data Index: 8421900 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.3401. Min Act: -0.1700

Data Index: 6139139 (Open Web Text)

Max Activating Token Index: 864

Text #16

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.4167. Min Act: -0.1700

Data Index: 2802274 (Open Web Text)

Max Activating Token Index: 907

Text #17

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.3786. Min Act: -0.1700

Data Index: 2480445 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.3658. Min Act: -0.1700

Data Index: 6169529 (Open Web Text)

Max Activating Token Index: 944

Text #19

Max Range: 2.4994. Min Range: -2.4994

Max Act: 2.3518. Min Act: -0.1700

Data Index: 5723577 (Open Web Text)

Max Activating Token Index: 941