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

Dataset: Open Web Text

Neuron 997 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: 4.5798. Min Range: -4.5798

Max Act: 4.5798. Min Act: -0.1700

Data Index: 1868194 (Open Web Text)

Max Activating Token Index: 736

Text #1

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.5338. Min Act: -0.1700

Data Index: 3797458 (Open Web Text)

Max Activating Token Index: 865

Text #2

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.5426. Min Act: -0.1700

Data Index: 1238840 (Open Web Text)

Max Activating Token Index: 703

Text #3

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.5013. Min Act: -0.1700

Data Index: 2516217 (Open Web Text)

Max Activating Token Index: 733

Text #4

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.4016. Min Act: -0.1700

Data Index: 1425636 (Open Web Text)

Max Activating Token Index: 302

Text #5

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.4196. Min Act: -0.1700

Data Index: 3908871 (Open Web Text)

Max Activating Token Index: 212

Text #6

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.4426. Min Act: -0.1700

Data Index: 1794522 (Open Web Text)

Max Activating Token Index: 213

Text #7

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.4272. Min Act: -0.1700

Data Index: 7524534 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.4091. Min Act: -0.1700

Data Index: 2785594 (Open Web Text)

Max Activating Token Index: 691

Text #9

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3842. Min Act: -0.1700

Data Index: 6286816 (Open Web Text)

Max Activating Token Index: 318

Text #10

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.4155. Min Act: -0.1700

Data Index: 5263758 (Open Web Text)

Max Activating Token Index: 351

Text #11

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.4084. Min Act: -0.1700

Data Index: 6830376 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3571. Min Act: -0.1700

Data Index: 6652402 (Open Web Text)

Max Activating Token Index: 728

Text #13

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3968. Min Act: -0.1700

Data Index: 7492004 (Open Web Text)

Max Activating Token Index: 580

Text #14

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3651. Min Act: -0.1700

Data Index: 6056294 (Open Web Text)

Max Activating Token Index: 904

Text #15

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3852. Min Act: -0.1700

Data Index: 5256521 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3755. Min Act: -0.1700

Data Index: 707315 (Open Web Text)

Max Activating Token Index: 812

Text #17

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3117. Min Act: -0.1700

Data Index: 3490633 (Open Web Text)

Max Activating Token Index: 875

Text #18

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3504. Min Act: -0.1700

Data Index: 119814 (Open Web Text)

Max Activating Token Index: 690

Text #19

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3519. Min Act: -0.1700

Data Index: 6292320 (Open Web Text)

Max Activating Token Index: 345