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

Dataset: Open Web Text

Neuron 1999 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: 4.2315. Min Range: -4.2315

Max Act: 4.2315. Min Act: -0.1700

Data Index: 1894920 (Open Web Text)

Max Activating Token Index: 518

Text #1

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.1612. Min Act: -0.1700

Data Index: 2898659 (Open Web Text)

Max Activating Token Index: 439

Text #2

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.1512. Min Act: -0.1700

Data Index: 3560846 (Open Web Text)

Max Activating Token Index: 440

Text #3

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.1848. Min Act: -0.1700

Data Index: 380508 (Open Web Text)

Max Activating Token Index: 539

Text #4

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.1097. Min Act: -0.1700

Data Index: 3340366 (Open Web Text)

Max Activating Token Index: 651

Text #5

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.1343. Min Act: -0.1700

Data Index: 67494 (Open Web Text)

Max Activating Token Index: 834

Text #6

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.1297. Min Act: -0.1700

Data Index: 32625 (Open Web Text)

Max Activating Token Index: 435

Text #7

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.1247. Min Act: -0.1700

Data Index: 8101727 (Open Web Text)

Max Activating Token Index: 879

Text #8

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0986. Min Act: -0.1700

Data Index: 1596243 (Open Web Text)

Max Activating Token Index: 335

Text #9

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0898. Min Act: -0.1700

Data Index: 4083669 (Open Web Text)

Max Activating Token Index: 466

Text #10

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0663. Min Act: -0.1700

Data Index: 3639290 (Open Web Text)

Max Activating Token Index: 405

Text #11

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0675. Min Act: -0.1700

Data Index: 7422471 (Open Web Text)

Max Activating Token Index: 323

Text #12

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0963. Min Act: -0.1700

Data Index: 5314252 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0978. Min Act: -0.1700

Data Index: 5467457 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0594. Min Act: -0.1700

Data Index: 5192401 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0706. Min Act: -0.1700

Data Index: 454226 (Open Web Text)

Max Activating Token Index: 552

Text #16

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0431. Min Act: -0.1700

Data Index: 4388326 (Open Web Text)

Max Activating Token Index: 892

Text #17

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0050. Min Act: -0.1700

Data Index: 91994 (Open Web Text)

Max Activating Token Index: 499

Text #18

Max Range: 4.2315. Min Range: -4.2315

Max Act: 4.0495. Min Act: -0.1700

Data Index: 5171072 (Open Web Text)

Max Activating Token Index: 94

Text #19

Max Range: 4.2315. Min Range: -4.2315

Max Act: 3.9914. Min Act: -0.1700

Data Index: 94154 (Open Web Text)

Max Activating Token Index: 49