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

Dataset: Open Web Text

Neuron 1496 in Layer 6

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: 3.6302. Min Range: -3.6302

Max Act: 3.6302. Min Act: -0.1700

Data Index: 6002750 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.6302. Min Range: -3.6302

Max Act: 3.2778. Min Act: -0.1700

Data Index: 7128804 (Open Web Text)

Max Activating Token Index: 187

Text #2

Max Range: 3.6302. Min Range: -3.6302

Max Act: 3.1351. Min Act: -0.1700

Data Index: 688260 (Open Web Text)

Max Activating Token Index: 515

Text #3

Max Range: 3.6302. Min Range: -3.6302

Max Act: 3.0697. Min Act: -0.1700

Data Index: 2027131 (Open Web Text)

Max Activating Token Index: 620

Text #4

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9950. Min Act: -0.1700

Data Index: 6724291 (Open Web Text)

Max Activating Token Index: 896

Text #5

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9692. Min Act: -0.1700

Data Index: 1451982 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9820. Min Act: -0.1700

Data Index: 3191427 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9711. Min Act: -0.1700

Data Index: 6625507 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9619. Min Act: -0.1700

Data Index: 1447756 (Open Web Text)

Max Activating Token Index: 808

Text #9

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9598. Min Act: -0.1700

Data Index: 5019337 (Open Web Text)

Max Activating Token Index: 339

Text #10

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9579. Min Act: -0.1700

Data Index: 1233601 (Open Web Text)

Max Activating Token Index: 706

Text #11

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9555. Min Act: -0.1700

Data Index: 7500007 (Open Web Text)

Max Activating Token Index: 952

Text #12

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9442. Min Act: -0.1700

Data Index: 2891566 (Open Web Text)

Max Activating Token Index: 301

Text #13

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9546. Min Act: -0.1700

Data Index: 635892 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9423. Min Act: -0.1700

Data Index: 7797991 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9438. Min Act: -0.1700

Data Index: 8043874 (Open Web Text)

Max Activating Token Index: 874

Text #16

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9369. Min Act: -0.1700

Data Index: 280647 (Open Web Text)

Max Activating Token Index: 351

Text #17

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9260. Min Act: -0.1700

Data Index: 6641878 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9268. Min Act: -0.1700

Data Index: 1780138 (Open Web Text)

Max Activating Token Index: 877

Text #19

Max Range: 3.6302. Min Range: -3.6302

Max Act: 2.9182. Min Act: -0.1700

Data Index: 6960211 (Open Web Text)

Max Activating Token Index: 499