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

Dataset: Open Web Text

Neuron 899 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: 4.2727. Min Range: -4.2727

Max Act: 4.2727. Min Act: -0.1700

Data Index: 5948067 (Open Web Text)

Max Activating Token Index: 342

Text #1

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.2216. Min Act: -0.1700

Data Index: 7815289 (Open Web Text)

Max Activating Token Index: 392

Text #2

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.1543. Min Act: -0.1700

Data Index: 2615897 (Open Web Text)

Max Activating Token Index: 196

Text #3

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.1126. Min Act: -0.1700

Data Index: 3978499 (Open Web Text)

Max Activating Token Index: 844

Text #4

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.1210. Min Act: -0.1700

Data Index: 6724178 (Open Web Text)

Max Activating Token Index: 130

Text #5

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.1061. Min Act: -0.1700

Data Index: 2699815 (Open Web Text)

Max Activating Token Index: 972

Text #6

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.1171. Min Act: -0.1700

Data Index: 7171673 (Open Web Text)

Max Activating Token Index: 549

Text #7

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.0998. Min Act: -0.1700

Data Index: 409680 (Open Web Text)

Max Activating Token Index: 736

Text #8

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.1246. Min Act: -0.1700

Data Index: 8471504 (Open Web Text)

Max Activating Token Index: 372

Text #9

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.1190. Min Act: -0.1700

Data Index: 840970 (Open Web Text)

Max Activating Token Index: 949

Text #10

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.1116. Min Act: -0.1700

Data Index: 5504021 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.1075. Min Act: -0.1700

Data Index: 5582291 (Open Web Text)

Max Activating Token Index: 956

Text #12

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.0574. Min Act: -0.1700

Data Index: 1671474 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.0590. Min Act: -0.1700

Data Index: 686964 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.0323. Min Act: -0.1700

Data Index: 1454836 (Open Web Text)

Max Activating Token Index: 352

Text #15

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.0324. Min Act: -0.1700

Data Index: 3667533 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.0550. Min Act: -0.1700

Data Index: 4555558 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.0186. Min Act: -0.1700

Data Index: 1766453 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 4.2727. Min Range: -4.2727

Max Act: 4.0085. Min Act: -0.1700

Data Index: 4942053 (Open Web Text)

Max Activating Token Index: 125

Text #19

Max Range: 4.2727. Min Range: -4.2727

Max Act: 3.9806. Min Act: -0.1700

Data Index: 3670131 (Open Web Text)

Max Activating Token Index: 129