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

Dataset: Open Web Text

Neuron 2597 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: 8.2168. Min Range: -8.2168

Max Act: 8.1897. Min Act: -0.1700

Data Index: 3402745 (Open Web Text)

Max Activating Token Index: 522

Text #1

Max Range: 8.2168. Min Range: -8.2168

Max Act: 8.2168. Min Act: -0.1700

Data Index: 5678631 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.8744. Min Act: -0.1700

Data Index: 1534838 (Open Web Text)

Max Activating Token Index: 698

Text #3

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.8453. Min Act: -0.1700

Data Index: 400098 (Open Web Text)

Max Activating Token Index: 768

Text #4

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.7914. Min Act: -0.1700

Data Index: 7244756 (Open Web Text)

Max Activating Token Index: 702

Text #5

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.7182. Min Act: -0.1700

Data Index: 4784632 (Open Web Text)

Max Activating Token Index: 915

Text #6

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.6332. Min Act: -0.1700

Data Index: 6020845 (Open Web Text)

Max Activating Token Index: 620

Text #7

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.6217. Min Act: -0.1700

Data Index: 6888917 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.6317. Min Act: -0.1700

Data Index: 6655279 (Open Web Text)

Max Activating Token Index: 419

Text #9

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.6306. Min Act: -0.1700

Data Index: 7817251 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.5454. Min Act: -0.1700

Data Index: 5945541 (Open Web Text)

Max Activating Token Index: 879

Text #11

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.6246. Min Act: -0.1700

Data Index: 147614 (Open Web Text)

Max Activating Token Index: 390

Text #12

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.4992. Min Act: -0.1700

Data Index: 2723900 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.5340. Min Act: -0.1700

Data Index: 2574631 (Open Web Text)

Max Activating Token Index: 957

Text #14

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.5256. Min Act: -0.1700

Data Index: 1119642 (Open Web Text)

Max Activating Token Index: 688

Text #15

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.4069. Min Act: -0.1700

Data Index: 3569221 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.4024. Min Act: -0.1700

Data Index: 753947 (Open Web Text)

Max Activating Token Index: 933

Text #17

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.4465. Min Act: -0.1700

Data Index: 1869708 (Open Web Text)

Max Activating Token Index: 388

Text #18

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.4730. Min Act: -0.1700

Data Index: 5239726 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 8.2168. Min Range: -8.2168

Max Act: 7.4523. Min Act: -0.1700

Data Index: 5568049 (Open Web Text)

Max Activating Token Index: 1019