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

Dataset: Open Web Text

Neuron 720 in Layer 0

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: 1.7538. Min Range: -1.7538

Max Act: 1.7538. Min Act: -0.1693

Data Index: 8690837 (Open Web Text)

Max Activating Token Index: 528

Text #1

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7422. Min Act: -0.1632

Data Index: 1156541 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7337. Min Act: -0.1666

Data Index: 5609623 (Open Web Text)

Max Activating Token Index: 190

Text #3

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7227. Min Act: -0.1700

Data Index: 4216254 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7175. Min Act: -0.1699

Data Index: 408296 (Open Web Text)

Max Activating Token Index: 326

Text #5

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.7205. Min Act: -0.1696

Data Index: 4693660 (Open Web Text)

Max Activating Token Index: 314

Text #6

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6789. Min Act: -0.1699

Data Index: 3467219 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6828. Min Act: -0.1683

Data Index: 3672251 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6840. Min Act: -0.1700

Data Index: 2736460 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6823. Min Act: -0.1699

Data Index: 839109 (Open Web Text)

Max Activating Token Index: 407

Text #10

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6786. Min Act: -0.1700

Data Index: 2917879 (Open Web Text)

Max Activating Token Index: 880

Text #11

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6643. Min Act: -0.1638

Data Index: 3091693 (Open Web Text)

Max Activating Token Index: 952

Text #12

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6663. Min Act: -0.1649

Data Index: 4529844 (Open Web Text)

Max Activating Token Index: 876

Text #13

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6625. Min Act: -0.1700

Data Index: 2420020 (Open Web Text)

Max Activating Token Index: 380

Text #14

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6638. Min Act: -0.1700

Data Index: 6145592 (Open Web Text)

Max Activating Token Index: 309

Text #15

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6526. Min Act: -0.1672

Data Index: 6731409 (Open Web Text)

Max Activating Token Index: 956

Text #16

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6431. Min Act: -0.1426

Data Index: 8150666 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6492. Min Act: -0.1686

Data Index: 6474060 (Open Web Text)

Max Activating Token Index: 551

Text #18

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6462. Min Act: -0.1700

Data Index: 8150667 (Open Web Text)

Max Activating Token Index: 159

Text #19

Max Range: 1.7538. Min Range: -1.7538

Max Act: 1.6417. Min Act: -0.1699

Data Index: 5405294 (Open Web Text)

Max Activating Token Index: 512