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

Dataset: Open Web Text

Neuron 2456 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: 3.1842. Min Range: -3.1842

Max Act: 3.1760. Min Act: -0.1700

Data Index: 1598051 (Open Web Text)

Max Activating Token Index: 345

Text #1

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1842. Min Act: -0.1700

Data Index: 5005009 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1580. Min Act: -0.1700

Data Index: 3662534 (Open Web Text)

Max Activating Token Index: 107

Text #3

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1637. Min Act: -0.1700

Data Index: 1086249 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1557. Min Act: -0.1700

Data Index: 7766699 (Open Web Text)

Max Activating Token Index: 639

Text #5

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1495. Min Act: -0.1700

Data Index: 5847769 (Open Web Text)

Max Activating Token Index: 408

Text #6

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1535. Min Act: -0.1700

Data Index: 3721135 (Open Web Text)

Max Activating Token Index: 513

Text #7

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1373. Min Act: -0.1700

Data Index: 8481779 (Open Web Text)

Max Activating Token Index: 92

Text #8

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1552. Min Act: -0.1700

Data Index: 431383 (Open Web Text)

Max Activating Token Index: 473

Text #9

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1555. Min Act: -0.1700

Data Index: 4743273 (Open Web Text)

Max Activating Token Index: 294

Text #10

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1176. Min Act: -0.1700

Data Index: 2810901 (Open Web Text)

Max Activating Token Index: 368

Text #11

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1294. Min Act: -0.1700

Data Index: 7095816 (Open Web Text)

Max Activating Token Index: 736

Text #12

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1085. Min Act: -0.1700

Data Index: 484708 (Open Web Text)

Max Activating Token Index: 132

Text #13

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1095. Min Act: -0.1700

Data Index: 1350305 (Open Web Text)

Max Activating Token Index: 759

Text #14

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1178. Min Act: -0.1700

Data Index: 1097186 (Open Web Text)

Max Activating Token Index: 577

Text #15

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1062. Min Act: -0.1700

Data Index: 4866782 (Open Web Text)

Max Activating Token Index: 165

Text #16

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1069. Min Act: -0.1700

Data Index: 7792877 (Open Web Text)

Max Activating Token Index: 224

Text #17

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1219. Min Act: -0.1700

Data Index: 5975418 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1067. Min Act: -0.1700

Data Index: 119044 (Open Web Text)

Max Activating Token Index: 232

Text #19

Max Range: 3.1842. Min Range: -3.1842

Max Act: 3.1102. Min Act: -0.1700

Data Index: 7066340 (Open Web Text)

Max Activating Token Index: 245