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

Dataset: Open Web Text

Neuron 519 in Layer 2

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: 6.1996. Min Range: -6.1996

Max Act: 6.1996. Min Act: -0.1700

Data Index: 1229843 (Open Web Text)

Max Activating Token Index: 353

Text #1

Max Range: 6.1996. Min Range: -6.1996

Max Act: 6.0134. Min Act: -0.1700

Data Index: 3637812 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.9464. Min Act: -0.1700

Data Index: 8181510 (Open Web Text)

Max Activating Token Index: 319

Text #3

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.7300. Min Act: -0.1700

Data Index: 1334353 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.6773. Min Act: -0.1700

Data Index: 282756 (Open Web Text)

Max Activating Token Index: 591

Text #5

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.6441. Min Act: -0.1700

Data Index: 627933 (Open Web Text)

Max Activating Token Index: 212

Text #6

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.6006. Min Act: -0.1700

Data Index: 6411659 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.6111. Min Act: -0.1700

Data Index: 290202 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.6278. Min Act: -0.1700

Data Index: 1653682 (Open Web Text)

Max Activating Token Index: 239

Text #9

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5825. Min Act: -0.1700

Data Index: 5659768 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5469. Min Act: -0.1700

Data Index: 4626777 (Open Web Text)

Max Activating Token Index: 170

Text #11

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5429. Min Act: -0.1700

Data Index: 1346058 (Open Web Text)

Max Activating Token Index: 392

Text #12

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5575. Min Act: -0.1700

Data Index: 1362950 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5387. Min Act: -0.1700

Data Index: 2827607 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5272. Min Act: -0.1700

Data Index: 3267181 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5105. Min Act: -0.1700

Data Index: 6756381 (Open Web Text)

Max Activating Token Index: 550

Text #16

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.4972. Min Act: -0.1700

Data Index: 7554153 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5285. Min Act: -0.1700

Data Index: 7659160 (Open Web Text)

Max Activating Token Index: 70

Text #18

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5378. Min Act: -0.1700

Data Index: 7684070 (Open Web Text)

Max Activating Token Index: 174

Text #19

Max Range: 6.1996. Min Range: -6.1996

Max Act: 5.5228. Min Act: -0.1700

Data Index: 5898925 (Open Web Text)

Max Activating Token Index: 33