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

Dataset: Open Web Text

Neuron 2779 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: 8.6398. Min Range: -8.6398

Max Act: 8.6398. Min Act: -0.1700

Data Index: 3478515 (Open Web Text)

Max Activating Token Index: 665

Text #1

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.7008. Min Act: -0.1700

Data Index: 5091435 (Open Web Text)

Max Activating Token Index: 633

Text #2

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.6650. Min Act: -0.1700

Data Index: 5333432 (Open Web Text)

Max Activating Token Index: 937

Text #3

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.5974. Min Act: -0.1700

Data Index: 6751488 (Open Web Text)

Max Activating Token Index: 533

Text #4

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.5900. Min Act: -0.1700

Data Index: 3154531 (Open Web Text)

Max Activating Token Index: 626

Text #5

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.4994. Min Act: -0.1700

Data Index: 8194119 (Open Web Text)

Max Activating Token Index: 982

Text #6

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.5826. Min Act: -0.1700

Data Index: 935175 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.4678. Min Act: -0.1700

Data Index: 188193 (Open Web Text)

Max Activating Token Index: 972

Text #8

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.5334. Min Act: -0.1700

Data Index: 3584391 (Open Web Text)

Max Activating Token Index: 985

Text #9

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3989. Min Act: -0.1700

Data Index: 8002015 (Open Web Text)

Max Activating Token Index: 956

Text #10

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3905. Min Act: -0.1700

Data Index: 1533343 (Open Web Text)

Max Activating Token Index: 143

Text #11

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3578. Min Act: -0.1700

Data Index: 5097948 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3664. Min Act: -0.1700

Data Index: 3535588 (Open Web Text)

Max Activating Token Index: 287

Text #13

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3640. Min Act: -0.1700

Data Index: 7714835 (Open Web Text)

Max Activating Token Index: 292

Text #14

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3628. Min Act: -0.1700

Data Index: 3689669 (Open Web Text)

Max Activating Token Index: 943

Text #15

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3712. Min Act: -0.1700

Data Index: 7974084 (Open Web Text)

Max Activating Token Index: 198

Text #16

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3964. Min Act: -0.1700

Data Index: 1034235 (Open Web Text)

Max Activating Token Index: 342

Text #17

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3051. Min Act: -0.1700

Data Index: 2768166 (Open Web Text)

Max Activating Token Index: 588

Text #18

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3130. Min Act: -0.1700

Data Index: 6044348 (Open Web Text)

Max Activating Token Index: 522

Text #19

Max Range: 8.6398. Min Range: -8.6398

Max Act: 7.3151. Min Act: -0.1700

Data Index: 109712 (Open Web Text)

Max Activating Token Index: 578