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

Dataset: Open Web Text

Neuron 2717 in Layer 3

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: 4.7202. Min Range: -4.7202

Max Act: 4.7202. Min Act: -0.1700

Data Index: 5467401 (Open Web Text)

Max Activating Token Index: 863

Text #1

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.6381. Min Act: -0.1700

Data Index: 3821508 (Open Web Text)

Max Activating Token Index: 901

Text #2

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.6051. Min Act: -0.1700

Data Index: 926931 (Open Web Text)

Max Activating Token Index: 877

Text #3

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.6708. Min Act: -0.1700

Data Index: 5705058 (Open Web Text)

Max Activating Token Index: 471

Text #4

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.6463. Min Act: -0.1700

Data Index: 6959898 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5981. Min Act: -0.1700

Data Index: 5096565 (Open Web Text)

Max Activating Token Index: 480

Text #6

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5969. Min Act: -0.1700

Data Index: 2270779 (Open Web Text)

Max Activating Token Index: 977

Text #7

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5974. Min Act: -0.1700

Data Index: 2308080 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5477. Min Act: -0.1700

Data Index: 773725 (Open Web Text)

Max Activating Token Index: 934

Text #9

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5624. Min Act: -0.1700

Data Index: 6929462 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5385. Min Act: -0.1700

Data Index: 3581531 (Open Web Text)

Max Activating Token Index: 85

Text #11

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5609. Min Act: -0.1700

Data Index: 2359240 (Open Web Text)

Max Activating Token Index: 511

Text #12

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5732. Min Act: -0.1700

Data Index: 1542080 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5238. Min Act: -0.1700

Data Index: 4331692 (Open Web Text)

Max Activating Token Index: 374

Text #14

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5765. Min Act: -0.1700

Data Index: 7100411 (Open Web Text)

Max Activating Token Index: 890

Text #15

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5159. Min Act: -0.1700

Data Index: 738275 (Open Web Text)

Max Activating Token Index: 415

Text #16

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5578. Min Act: -0.1700

Data Index: 4845618 (Open Web Text)

Max Activating Token Index: 727

Text #17

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5266. Min Act: -0.1700

Data Index: 1215848 (Open Web Text)

Max Activating Token Index: 455

Text #18

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5363. Min Act: -0.1700

Data Index: 1493387 (Open Web Text)

Max Activating Token Index: 662

Text #19

Max Range: 4.7202. Min Range: -4.7202

Max Act: 4.5259. Min Act: -0.1700

Data Index: 587969 (Open Web Text)

Max Activating Token Index: 807