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

Dataset: Open Web Text

Neuron 1515 in Layer 5

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: 4.8066. Min Range: -4.8066

Max Act: 4.7824. Min Act: -0.1700

Data Index: 6765255 (Open Web Text)

Max Activating Token Index: 445

Text #1

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.8066. Min Act: -0.1700

Data Index: 4124103 (Open Web Text)

Max Activating Token Index: 89

Text #2

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7916. Min Act: -0.1700

Data Index: 2211570 (Open Web Text)

Max Activating Token Index: 309

Text #3

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7804. Min Act: -0.1700

Data Index: 6194352 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7853. Min Act: -0.1700

Data Index: 5900174 (Open Web Text)

Max Activating Token Index: 664

Text #5

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7459. Min Act: -0.1700

Data Index: 3053624 (Open Web Text)

Max Activating Token Index: 654

Text #6

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7444. Min Act: -0.1700

Data Index: 287998 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7218. Min Act: -0.1700

Data Index: 5158849 (Open Web Text)

Max Activating Token Index: 389

Text #8

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6892. Min Act: -0.1700

Data Index: 5013299 (Open Web Text)

Max Activating Token Index: 320

Text #9

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.7144. Min Act: -0.1700

Data Index: 4220979 (Open Web Text)

Max Activating Token Index: 967

Text #10

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6992. Min Act: -0.1700

Data Index: 903431 (Open Web Text)

Max Activating Token Index: 192

Text #11

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6700. Min Act: -0.1700

Data Index: 829048 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6679. Min Act: -0.1700

Data Index: 731928 (Open Web Text)

Max Activating Token Index: 571

Text #13

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6636. Min Act: -0.1700

Data Index: 3229920 (Open Web Text)

Max Activating Token Index: 250

Text #14

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6861. Min Act: -0.1700

Data Index: 1929389 (Open Web Text)

Max Activating Token Index: 138

Text #15

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6847. Min Act: -0.1700

Data Index: 5809974 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6920. Min Act: -0.1700

Data Index: 1539032 (Open Web Text)

Max Activating Token Index: 574

Text #17

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6829. Min Act: -0.1700

Data Index: 410180 (Open Web Text)

Max Activating Token Index: 230

Text #18

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6807. Min Act: -0.1700

Data Index: 3988909 (Open Web Text)

Max Activating Token Index: 449

Text #19

Max Range: 4.8066. Min Range: -4.8066

Max Act: 4.6786. Min Act: -0.1700

Data Index: 5924122 (Open Web Text)

Max Activating Token Index: 4