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

Dataset: Open Web Text

Neuron 1283 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: 1.8593. Min Range: -1.8593

Max Act: 1.8593. Min Act: -0.1700

Data Index: 619250 (Open Web Text)

Max Activating Token Index: 323

Text #1

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7436. Min Act: -0.1700

Data Index: 1335300 (Open Web Text)

Max Activating Token Index: 412

Text #2

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7344. Min Act: -0.1700

Data Index: 7068074 (Open Web Text)

Max Activating Token Index: 148

Text #3

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7266. Min Act: -0.1700

Data Index: 3462205 (Open Web Text)

Max Activating Token Index: 398

Text #4

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7201. Min Act: -0.1700

Data Index: 2359732 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7025. Min Act: -0.1700

Data Index: 3626466 (Open Web Text)

Max Activating Token Index: 804

Text #6

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7152. Min Act: -0.1700

Data Index: 2505836 (Open Web Text)

Max Activating Token Index: 230

Text #7

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6932. Min Act: -0.1700

Data Index: 6823578 (Open Web Text)

Max Activating Token Index: 420

Text #8

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6821. Min Act: -0.1700

Data Index: 5583694 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6962. Min Act: -0.1700

Data Index: 4062451 (Open Web Text)

Max Activating Token Index: 128

Text #10

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6841. Min Act: -0.1700

Data Index: 6695279 (Open Web Text)

Max Activating Token Index: 722

Text #11

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6771. Min Act: -0.1700

Data Index: 7652450 (Open Web Text)

Max Activating Token Index: 34

Text #12

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6769. Min Act: -0.1700

Data Index: 1756577 (Open Web Text)

Max Activating Token Index: 347

Text #13

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6576. Min Act: -0.1699

Data Index: 4764848 (Open Web Text)

Max Activating Token Index: 672

Text #14

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6682. Min Act: -0.1700

Data Index: 7375655 (Open Web Text)

Max Activating Token Index: 991

Text #15

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6663. Min Act: -0.1700

Data Index: 2992264 (Open Web Text)

Max Activating Token Index: 466

Text #16

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6663. Min Act: -0.1700

Data Index: 6750476 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6593. Min Act: -0.1700

Data Index: 1681494 (Open Web Text)

Max Activating Token Index: 695

Text #18

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6507. Min Act: -0.1700

Data Index: 7354655 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6611. Min Act: -0.1700

Data Index: 845826 (Open Web Text)

Max Activating Token Index: 236