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

Dataset: Open Web Text

Neuron 1719 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: 4.3876. Min Range: -4.3876

Max Act: 4.3876. Min Act: -0.1700

Data Index: 8054639 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.3876. Min Act: -0.1700

Data Index: 6285330 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.3876. Min Act: -0.1700

Data Index: 8714575 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.3836. Min Act: -0.1700

Data Index: 6916134 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.3222. Min Act: -0.1700

Data Index: 1531620 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2957. Min Act: -0.1700

Data Index: 1376526 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2776. Min Act: -0.1700

Data Index: 7160634 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2606. Min Act: -0.1700

Data Index: 8019148 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2516. Min Act: -0.1700

Data Index: 2509605 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2559. Min Act: -0.1700

Data Index: 2544245 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2389. Min Act: -0.1700

Data Index: 2540227 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2423. Min Act: -0.1700

Data Index: 1121793 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2294. Min Act: -0.1700

Data Index: 4473308 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2252. Min Act: -0.1700

Data Index: 712259 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2043. Min Act: -0.1700

Data Index: 5931509 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2129. Min Act: -0.1700

Data Index: 2486860 (Open Web Text)

Max Activating Token Index: 32

Text #16

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2043. Min Act: -0.1700

Data Index: 1001422 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2327. Min Act: -0.1700

Data Index: 5327629 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2005. Min Act: -0.1700

Data Index: 1547643 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.3876. Min Range: -4.3876

Max Act: 4.2006. Min Act: -0.1700

Data Index: 2626365 (Open Web Text)

Max Activating Token Index: 3