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

Dataset: Open Web Text

Neuron 162 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: 4.2267. Min Range: -4.2267

Max Act: 4.2267. Min Act: -0.1700

Data Index: 6921031 (Open Web Text)

Max Activating Token Index: 239

Text #1

Max Range: 4.2267. Min Range: -4.2267

Max Act: 4.1540. Min Act: -0.1700

Data Index: 7834023 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 4.2267. Min Range: -4.2267

Max Act: 4.0134. Min Act: -0.1700

Data Index: 2910070 (Open Web Text)

Max Activating Token Index: 393

Text #3

Max Range: 4.2267. Min Range: -4.2267

Max Act: 4.1074. Min Act: -0.1700

Data Index: 3258907 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 4.2267. Min Range: -4.2267

Max Act: 4.0165. Min Act: -0.1700

Data Index: 7416575 (Open Web Text)

Max Activating Token Index: 491

Text #5

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9686. Min Act: -0.1700

Data Index: 6301185 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9546. Min Act: -0.1700

Data Index: 1460664 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9741. Min Act: -0.1700

Data Index: 6713650 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9578. Min Act: -0.1700

Data Index: 1752307 (Open Web Text)

Max Activating Token Index: 645

Text #9

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9783. Min Act: -0.1700

Data Index: 2230910 (Open Web Text)

Max Activating Token Index: 165

Text #10

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9865. Min Act: -0.1700

Data Index: 2107815 (Open Web Text)

Max Activating Token Index: 462

Text #11

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9440. Min Act: -0.1700

Data Index: 5598144 (Open Web Text)

Max Activating Token Index: 252

Text #12

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9360. Min Act: -0.1700

Data Index: 2549985 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9275. Min Act: -0.1700

Data Index: 8675996 (Open Web Text)

Max Activating Token Index: 154

Text #14

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9258. Min Act: -0.1700

Data Index: 7337152 (Open Web Text)

Max Activating Token Index: 584

Text #15

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9218. Min Act: -0.1700

Data Index: 2092553 (Open Web Text)

Max Activating Token Index: 308

Text #16

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9304. Min Act: -0.1700

Data Index: 1598703 (Open Web Text)

Max Activating Token Index: 949

Text #17

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9214. Min Act: -0.1700

Data Index: 1096666 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9036. Min Act: -0.1700

Data Index: 7779694 (Open Web Text)

Max Activating Token Index: 124

Text #19

Max Range: 4.2267. Min Range: -4.2267

Max Act: 3.9207. Min Act: -0.1700

Data Index: 2858909 (Open Web Text)

Max Activating Token Index: 100