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

Dataset: Open Web Text

Neuron 20 in Layer 2

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: 1.5195. Min Range: -1.5195

Max Act: 1.5195. Min Act: -0.1700

Data Index: 5612354 (Open Web Text)

Max Activating Token Index: 386

Text #1

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4736. Min Act: -0.1700

Data Index: 3724635 (Open Web Text)

Max Activating Token Index: 699

Text #2

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4797. Min Act: -0.1700

Data Index: 5631699 (Open Web Text)

Max Activating Token Index: 116

Text #3

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4723. Min Act: -0.1700

Data Index: 2520819 (Open Web Text)

Max Activating Token Index: 368

Text #4

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4771. Min Act: -0.1700

Data Index: 7913103 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4570. Min Act: -0.1700

Data Index: 592690 (Open Web Text)

Max Activating Token Index: 171

Text #6

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4587. Min Act: -0.1700

Data Index: 1743838 (Open Web Text)

Max Activating Token Index: 868

Text #7

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4583. Min Act: -0.1700

Data Index: 640083 (Open Web Text)

Max Activating Token Index: 417

Text #8

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4536. Min Act: -0.1700

Data Index: 6048444 (Open Web Text)

Max Activating Token Index: 908

Text #9

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4450. Min Act: -0.1700

Data Index: 7379630 (Open Web Text)

Max Activating Token Index: 818

Text #10

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4459. Min Act: -0.1700

Data Index: 550019 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4451. Min Act: -0.1700

Data Index: 5066696 (Open Web Text)

Max Activating Token Index: 893

Text #12

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4415. Min Act: -0.1699

Data Index: 2718542 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4354. Min Act: -0.1700

Data Index: 1979807 (Open Web Text)

Max Activating Token Index: 964

Text #14

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4386. Min Act: -0.1700

Data Index: 8147824 (Open Web Text)

Max Activating Token Index: 108

Text #15

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4267. Min Act: -0.1700

Data Index: 8595418 (Open Web Text)

Max Activating Token Index: 833

Text #16

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4443. Min Act: -0.1695

Data Index: 6314227 (Open Web Text)

Max Activating Token Index: 338

Text #17

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4394. Min Act: -0.1696

Data Index: 71791 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4493. Min Act: -0.1700

Data Index: 5048485 (Open Web Text)

Max Activating Token Index: 341

Text #19

Max Range: 1.5195. Min Range: -1.5195

Max Act: 1.4292. Min Act: -0.1700

Data Index: 3767143 (Open Web Text)

Max Activating Token Index: 17