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

Dataset: Open Web Text

Neuron 2265 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: 4.5128. Min Range: -4.5128

Max Act: 4.5128. Min Act: -0.1700

Data Index: 274999 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.4955. Min Act: -0.1700

Data Index: 8053350 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.4699. Min Act: -0.1700

Data Index: 906713 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.4212. Min Act: -0.1695

Data Index: 7936063 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.4303. Min Act: -0.1700

Data Index: 808372 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3943. Min Act: -0.1700

Data Index: 1406082 (Open Web Text)

Max Activating Token Index: 256

Text #6

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3756. Min Act: -0.1700

Data Index: 196692 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3870. Min Act: -0.1700

Data Index: 4529469 (Open Web Text)

Max Activating Token Index: 440

Text #8

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3852. Min Act: -0.1700

Data Index: 736906 (Open Web Text)

Max Activating Token Index: 354

Text #9

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.4012. Min Act: -0.1699

Data Index: 6274026 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.4092. Min Act: -0.1700

Data Index: 6726387 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3721. Min Act: -0.1700

Data Index: 928547 (Open Web Text)

Max Activating Token Index: 785

Text #12

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3386. Min Act: -0.1700

Data Index: 1588284 (Open Web Text)

Max Activating Token Index: 569

Text #13

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3405. Min Act: -0.1700

Data Index: 4384377 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3736. Min Act: -0.1700

Data Index: 988649 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3454. Min Act: -0.1700

Data Index: 1842595 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3524. Min Act: -0.1700

Data Index: 1848328 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3507. Min Act: -0.1700

Data Index: 5176612 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3511. Min Act: -0.1700

Data Index: 5468327 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.5128. Min Range: -4.5128

Max Act: 4.3587. Min Act: -0.1700

Data Index: 5690768 (Open Web Text)

Max Activating Token Index: 484