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

Dataset: Open Web Text

Neuron 1349 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: 1.7778. Min Range: -1.7778

Max Act: 1.7778. Min Act: -0.1700

Data Index: 962577 (Open Web Text)

Max Activating Token Index: 908

Text #1

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7657. Min Act: -0.1700

Data Index: 7336493 (Open Web Text)

Max Activating Token Index: 377

Text #2

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7567. Min Act: -0.1700

Data Index: 6818021 (Open Web Text)

Max Activating Token Index: 200

Text #3

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7613. Min Act: -0.1700

Data Index: 2412849 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7641. Min Act: -0.1700

Data Index: 4357073 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7469. Min Act: -0.1700

Data Index: 4914130 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7565. Min Act: -0.1700

Data Index: 3037374 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7436. Min Act: -0.1700

Data Index: 4133925 (Open Web Text)

Max Activating Token Index: 481

Text #8

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7488. Min Act: -0.1700

Data Index: 8513716 (Open Web Text)

Max Activating Token Index: 665

Text #9

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7418. Min Act: -0.1700

Data Index: 7115739 (Open Web Text)

Max Activating Token Index: 792

Text #10

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7484. Min Act: -0.1700

Data Index: 7251693 (Open Web Text)

Max Activating Token Index: 327

Text #11

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7420. Min Act: -0.1700

Data Index: 231370 (Open Web Text)

Max Activating Token Index: 41

Text #12

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7421. Min Act: -0.1700

Data Index: 4738229 (Open Web Text)

Max Activating Token Index: 985

Text #13

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7314. Min Act: -0.1700

Data Index: 2268496 (Open Web Text)

Max Activating Token Index: 209

Text #14

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7196. Min Act: -0.1700

Data Index: 5677441 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7210. Min Act: -0.1700

Data Index: 2217581 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7275. Min Act: -0.1700

Data Index: 208715 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7198. Min Act: -0.1700

Data Index: 7194705 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7228. Min Act: -0.1695

Data Index: 2772611 (Open Web Text)

Max Activating Token Index: 238

Text #19

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7285. Min Act: -0.1697

Data Index: 4137121 (Open Web Text)

Max Activating Token Index: 582