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

Dataset: Open Web Text

Neuron 1419 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: 3.6694. Min Range: -3.6694

Max Act: 3.6650. Min Act: -0.1700

Data Index: 6725841 (Open Web Text)

Max Activating Token Index: 71

Text #1

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6694. Min Act: -0.1700

Data Index: 4496003 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6694. Min Act: -0.1700

Data Index: 1277068 (Open Web Text)

Max Activating Token Index: 847

Text #3

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6593. Min Act: -0.1700

Data Index: 5394201 (Open Web Text)

Max Activating Token Index: 365

Text #4

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6382. Min Act: -0.1700

Data Index: 4468452 (Open Web Text)

Max Activating Token Index: 293

Text #5

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6158. Min Act: -0.1700

Data Index: 7493686 (Open Web Text)

Max Activating Token Index: 950

Text #6

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6377. Min Act: -0.1700

Data Index: 6375597 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5891. Min Act: -0.1700

Data Index: 8241356 (Open Web Text)

Max Activating Token Index: 610

Text #8

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6121. Min Act: -0.1700

Data Index: 1461139 (Open Web Text)

Max Activating Token Index: 507

Text #9

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6080. Min Act: -0.1700

Data Index: 3277715 (Open Web Text)

Max Activating Token Index: 441

Text #10

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6130. Min Act: -0.1700

Data Index: 1742120 (Open Web Text)

Max Activating Token Index: 393

Text #11

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5877. Min Act: -0.1700

Data Index: 8159659 (Open Web Text)

Max Activating Token Index: 775

Text #12

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5988. Min Act: -0.1700

Data Index: 1464546 (Open Web Text)

Max Activating Token Index: 314

Text #13

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5735. Min Act: -0.1700

Data Index: 1631679 (Open Web Text)

Max Activating Token Index: 636

Text #14

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5897. Min Act: -0.1700

Data Index: 5498685 (Open Web Text)

Max Activating Token Index: 121

Text #15

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5667. Min Act: -0.1700

Data Index: 1603404 (Open Web Text)

Max Activating Token Index: 932

Text #16

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5517. Min Act: -0.1700

Data Index: 1952659 (Open Web Text)

Max Activating Token Index: 458

Text #17

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5746. Min Act: -0.1700

Data Index: 1122713 (Open Web Text)

Max Activating Token Index: 727

Text #18

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5679. Min Act: -0.1700

Data Index: 3475191 (Open Web Text)

Max Activating Token Index: 1002

Text #19

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5645. Min Act: -0.1700

Data Index: 6699212 (Open Web Text)

Max Activating Token Index: 417