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

Dataset: Open Web Text

Neuron 761 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: 6.4289. Min Range: -6.4289

Max Act: 6.4289. Min Act: -0.1700

Data Index: 3312926 (Open Web Text)

Max Activating Token Index: 407

Text #1

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.3832. Min Act: -0.1700

Data Index: 992388 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.4228. Min Act: -0.1700

Data Index: 8555669 (Open Web Text)

Max Activating Token Index: 1018

Text #3

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.3935. Min Act: -0.1700

Data Index: 419234 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.3244. Min Act: -0.1700

Data Index: 5291564 (Open Web Text)

Max Activating Token Index: 135

Text #5

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.2717. Min Act: -0.1700

Data Index: 4762497 (Open Web Text)

Max Activating Token Index: 424

Text #6

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.3052. Min Act: -0.1700

Data Index: 4016490 (Open Web Text)

Max Activating Token Index: 775

Text #7

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.2575. Min Act: -0.1700

Data Index: 4184221 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.2513. Min Act: -0.1700

Data Index: 4399526 (Open Web Text)

Max Activating Token Index: 695

Text #9

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.1834. Min Act: -0.1700

Data Index: 3587338 (Open Web Text)

Max Activating Token Index: 811

Text #10

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.2674. Min Act: -0.1700

Data Index: 2640849 (Open Web Text)

Max Activating Token Index: 823

Text #11

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.2616. Min Act: -0.1700

Data Index: 6923525 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.2180. Min Act: -0.1700

Data Index: 6845492 (Open Web Text)

Max Activating Token Index: 195

Text #13

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.2052. Min Act: -0.1700

Data Index: 1776688 (Open Web Text)

Max Activating Token Index: 261

Text #14

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.1915. Min Act: -0.1700

Data Index: 281495 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.1730. Min Act: -0.1700

Data Index: 396599 (Open Web Text)

Max Activating Token Index: 616

Text #16

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.1550. Min Act: -0.1700

Data Index: 8311000 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.1288. Min Act: -0.1700

Data Index: 2160067 (Open Web Text)

Max Activating Token Index: 449

Text #18

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.1529. Min Act: -0.1700

Data Index: 2611862 (Open Web Text)

Max Activating Token Index: 766

Text #19

Max Range: 6.4289. Min Range: -6.4289

Max Act: 6.1591. Min Act: -0.1700

Data Index: 6149115 (Open Web Text)

Max Activating Token Index: 910