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

Dataset: Open Web Text

Neuron 3004 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: 2.0309. Min Range: -2.0309

Max Act: 2.0309. Min Act: -0.1676

Data Index: 755088 (Open Web Text)

Max Activating Token Index: 321

Text #1

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.9707. Min Act: -0.1700

Data Index: 8011358 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.9489. Min Act: -0.1700

Data Index: 7479957 (Open Web Text)

Max Activating Token Index: 546

Text #3

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.9287. Min Act: -0.1694

Data Index: 5246753 (Open Web Text)

Max Activating Token Index: 278

Text #4

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.9261. Min Act: -0.1700

Data Index: 7784638 (Open Web Text)

Max Activating Token Index: 175

Text #5

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.9302. Min Act: -0.1700

Data Index: 7914475 (Open Web Text)

Max Activating Token Index: 880

Text #6

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.9040. Min Act: -0.1700

Data Index: 5007152 (Open Web Text)

Max Activating Token Index: 1006

Text #7

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.9005. Min Act: -0.1694

Data Index: 7864639 (Open Web Text)

Max Activating Token Index: 432

Text #8

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8913. Min Act: -0.1700

Data Index: 1727525 (Open Web Text)

Max Activating Token Index: 343

Text #9

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8953. Min Act: -0.1684

Data Index: 1064239 (Open Web Text)

Max Activating Token Index: 621

Text #10

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8905. Min Act: -0.1700

Data Index: 3641893 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8859. Min Act: -0.1655

Data Index: 3912132 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8823. Min Act: -0.1700

Data Index: 1727524 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8583. Min Act: -0.1700

Data Index: 6493963 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8670. Min Act: -0.1700

Data Index: 6785879 (Open Web Text)

Max Activating Token Index: 269

Text #15

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8451. Min Act: -0.1700

Data Index: 374304 (Open Web Text)

Max Activating Token Index: 679

Text #16

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8517. Min Act: -0.1700

Data Index: 1268501 (Open Web Text)

Max Activating Token Index: 395

Text #17

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8488. Min Act: -0.1685

Data Index: 8240310 (Open Web Text)

Max Activating Token Index: 263

Text #18

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8386. Min Act: -0.1689

Data Index: 2718458 (Open Web Text)

Max Activating Token Index: 725

Text #19

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8383. Min Act: -0.1700

Data Index: 870705 (Open Web Text)

Max Activating Token Index: 383