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

Dataset: Open Web Text

Neuron 648 in Layer 5

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: 3.6905. Min Range: -3.6905

Max Act: 3.6905. Min Act: -0.1700

Data Index: 4442320 (Open Web Text)

Max Activating Token Index: 278

Text #1

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4861. Min Act: -0.1700

Data Index: 4679396 (Open Web Text)

Max Activating Token Index: 384

Text #2

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4773. Min Act: -0.1700

Data Index: 1988223 (Open Web Text)

Max Activating Token Index: 980

Text #3

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4684. Min Act: -0.1700

Data Index: 6564688 (Open Web Text)

Max Activating Token Index: 41

Text #4

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4644. Min Act: -0.1700

Data Index: 6678547 (Open Web Text)

Max Activating Token Index: 689

Text #5

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4511. Min Act: -0.1700

Data Index: 7913975 (Open Web Text)

Max Activating Token Index: 747

Text #6

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4384. Min Act: -0.1700

Data Index: 5941413 (Open Web Text)

Max Activating Token Index: 1003

Text #7

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4382. Min Act: -0.1700

Data Index: 5248623 (Open Web Text)

Max Activating Token Index: 239

Text #8

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.3973. Min Act: -0.1700

Data Index: 633680 (Open Web Text)

Max Activating Token Index: 220

Text #9

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.3845. Min Act: -0.1700

Data Index: 580890 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.3490. Min Act: -0.1700

Data Index: 2864220 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.3476. Min Act: -0.1700

Data Index: 4191360 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.3555. Min Act: -0.1700

Data Index: 6946408 (Open Web Text)

Max Activating Token Index: 776

Text #13

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.3296. Min Act: -0.1700

Data Index: 6956793 (Open Web Text)

Max Activating Token Index: 989

Text #14

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.3394. Min Act: -0.1700

Data Index: 339327 (Open Web Text)

Max Activating Token Index: 783

Text #15

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.2466. Min Act: -0.1700

Data Index: 8239387 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.2672. Min Act: -0.1700

Data Index: 969208 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.3110. Min Act: -0.1700

Data Index: 6910492 (Open Web Text)

Max Activating Token Index: 450

Text #18

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.2619. Min Act: -0.1700

Data Index: 7993369 (Open Web Text)

Max Activating Token Index: 161

Text #19

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.2707. Min Act: -0.1700

Data Index: 5754246 (Open Web Text)

Max Activating Token Index: 396