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

Dataset: Open Web Text

Neuron 776 in Layer 4

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: 4.7361. Min Range: -4.7361

Max Act: 4.7361. Min Act: -0.1700

Data Index: 7369482 (Open Web Text)

Max Activating Token Index: 695

Text #1

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.5217. Min Act: -0.1700

Data Index: 6878283 (Open Web Text)

Max Activating Token Index: 733

Text #2

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.5061. Min Act: -0.1700

Data Index: 8479862 (Open Web Text)

Max Activating Token Index: 522

Text #3

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.4889. Min Act: -0.1700

Data Index: 2258268 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.4615. Min Act: -0.1700

Data Index: 2979614 (Open Web Text)

Max Activating Token Index: 891

Text #5

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.4130. Min Act: -0.1700

Data Index: 8632391 (Open Web Text)

Max Activating Token Index: 843

Text #6

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.4252. Min Act: -0.1700

Data Index: 7297709 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.3377. Min Act: -0.1700

Data Index: 5296201 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.3970. Min Act: -0.1700

Data Index: 3688783 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.4223. Min Act: -0.1700

Data Index: 5633904 (Open Web Text)

Max Activating Token Index: 976

Text #10

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.4225. Min Act: -0.1700

Data Index: 7312138 (Open Web Text)

Max Activating Token Index: 744

Text #11

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.4205. Min Act: -0.1700

Data Index: 4831842 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.4021. Min Act: -0.1700

Data Index: 1781088 (Open Web Text)

Max Activating Token Index: 631

Text #13

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.4068. Min Act: -0.1700

Data Index: 3317344 (Open Web Text)

Max Activating Token Index: 234

Text #14

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.3708. Min Act: -0.1700

Data Index: 371819 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.3041. Min Act: -0.1700

Data Index: 8265120 (Open Web Text)

Max Activating Token Index: 1016

Text #16

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.3845. Min Act: -0.1700

Data Index: 8323023 (Open Web Text)

Max Activating Token Index: 564

Text #17

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.3682. Min Act: -0.1700

Data Index: 8581338 (Open Web Text)

Max Activating Token Index: 554

Text #18

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.3414. Min Act: -0.1700

Data Index: 2968122 (Open Web Text)

Max Activating Token Index: 621

Text #19

Max Range: 4.7361. Min Range: -4.7361

Max Act: 4.3586. Min Act: -0.1700

Data Index: 4283873 (Open Web Text)

Max Activating Token Index: 216