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

Dataset: Open Web Text

Neuron 770 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: 4.8460. Min Range: -4.8460

Max Act: 4.8460. Min Act: -0.1700

Data Index: 5183982 (Open Web Text)

Max Activating Token Index: 989

Text #1

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.8350. Min Act: -0.1700

Data Index: 7722430 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.8012. Min Act: -0.1700

Data Index: 1722192 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7649. Min Act: -0.1700

Data Index: 4785884 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7658. Min Act: -0.1700

Data Index: 3823302 (Open Web Text)

Max Activating Token Index: 720

Text #5

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7286. Min Act: -0.1700

Data Index: 143521 (Open Web Text)

Max Activating Token Index: 320

Text #6

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7469. Min Act: -0.1700

Data Index: 1693794 (Open Web Text)

Max Activating Token Index: 267

Text #7

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7064. Min Act: -0.1700

Data Index: 1693414 (Open Web Text)

Max Activating Token Index: 881

Text #8

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7230. Min Act: -0.1700

Data Index: 684530 (Open Web Text)

Max Activating Token Index: 819

Text #9

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7094. Min Act: -0.1700

Data Index: 6878043 (Open Web Text)

Max Activating Token Index: 893

Text #10

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7340. Min Act: -0.1700

Data Index: 2779813 (Open Web Text)

Max Activating Token Index: 182

Text #11

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6926. Min Act: -0.1700

Data Index: 8551775 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6871. Min Act: -0.1700

Data Index: 5031521 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7024. Min Act: -0.1700

Data Index: 3203271 (Open Web Text)

Max Activating Token Index: 954

Text #14

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6888. Min Act: -0.1700

Data Index: 6935027 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6702. Min Act: -0.1700

Data Index: 7385222 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6886. Min Act: -0.1700

Data Index: 2531364 (Open Web Text)

Max Activating Token Index: 398

Text #17

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6541. Min Act: -0.1700

Data Index: 5397976 (Open Web Text)

Max Activating Token Index: 805

Text #18

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6553. Min Act: -0.1700

Data Index: 3466600 (Open Web Text)

Max Activating Token Index: 849

Text #19

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6455. Min Act: -0.1700

Data Index: 1938858 (Open Web Text)

Max Activating Token Index: 478