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

Dataset: Open Web Text

Neuron 1211 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: 1.6268. Min Range: -1.6268

Max Act: 1.6268. Min Act: -0.1700

Data Index: 1472604 (Open Web Text)

Max Activating Token Index: 352

Text #1

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.6245. Min Act: -0.1700

Data Index: 2038765 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5777. Min Act: -0.1695

Data Index: 3132942 (Open Web Text)

Max Activating Token Index: 685

Text #3

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5705. Min Act: -0.1697

Data Index: 4193742 (Open Web Text)

Max Activating Token Index: 89

Text #4

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5731. Min Act: -0.1689

Data Index: 559670 (Open Web Text)

Max Activating Token Index: 144

Text #5

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5702. Min Act: -0.1700

Data Index: 301633 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5713. Min Act: -0.1700

Data Index: 7463277 (Open Web Text)

Max Activating Token Index: 192

Text #7

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5567. Min Act: -0.1699

Data Index: 7346035 (Open Web Text)

Max Activating Token Index: 288

Text #8

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5599. Min Act: -0.1700

Data Index: 1426379 (Open Web Text)

Max Activating Token Index: 319

Text #9

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5488. Min Act: -0.1700

Data Index: 4711318 (Open Web Text)

Max Activating Token Index: 744

Text #10

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5548. Min Act: -0.1700

Data Index: 1888218 (Open Web Text)

Max Activating Token Index: 227

Text #11

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5490. Min Act: -0.1700

Data Index: 2336929 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5446. Min Act: -0.1700

Data Index: 2812838 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5277. Min Act: -0.1700

Data Index: 8239679 (Open Web Text)

Max Activating Token Index: 40

Text #14

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5313. Min Act: -0.1700

Data Index: 977222 (Open Web Text)

Max Activating Token Index: 81

Text #15

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5349. Min Act: -0.1700

Data Index: 1515056 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5370. Min Act: -0.1698

Data Index: 8652850 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5223. Min Act: -0.1700

Data Index: 2171757 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5288. Min Act: -0.1700

Data Index: 3183809 (Open Web Text)

Max Activating Token Index: 65

Text #19

Max Range: 1.6268. Min Range: -1.6268

Max Act: 1.5329. Min Act: -0.1700

Data Index: 8259572 (Open Web Text)

Max Activating Token Index: 234