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

Dataset: Open Web Text

Neuron 917 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: 6.1274. Min Range: -6.1274

Max Act: 6.1274. Min Act: -0.1700

Data Index: 6478458 (Open Web Text)

Max Activating Token Index: 893

Text #1

Max Range: 6.1274. Min Range: -6.1274

Max Act: 6.1015. Min Act: -0.1700

Data Index: 6580260 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 6.1274. Min Range: -6.1274

Max Act: 6.0612. Min Act: -0.1700

Data Index: 573332 (Open Web Text)

Max Activating Token Index: 366

Text #3

Max Range: 6.1274. Min Range: -6.1274

Max Act: 6.0697. Min Act: -0.1700

Data Index: 254158 (Open Web Text)

Max Activating Token Index: 817

Text #4

Max Range: 6.1274. Min Range: -6.1274

Max Act: 6.0178. Min Act: -0.1700

Data Index: 588642 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 6.1274. Min Range: -6.1274

Max Act: 6.0305. Min Act: -0.1700

Data Index: 19882 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 6.1274. Min Range: -6.1274

Max Act: 6.0076. Min Act: -0.1700

Data Index: 2355097 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9909. Min Act: -0.1700

Data Index: 3045581 (Open Web Text)

Max Activating Token Index: 771

Text #8

Max Range: 6.1274. Min Range: -6.1274

Max Act: 6.0078. Min Act: -0.1700

Data Index: 4851037 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9969. Min Act: -0.1700

Data Index: 1650171 (Open Web Text)

Max Activating Token Index: 78

Text #10

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9686. Min Act: -0.1700

Data Index: 627854 (Open Web Text)

Max Activating Token Index: 175

Text #11

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9696. Min Act: -0.1700

Data Index: 6026597 (Open Web Text)

Max Activating Token Index: 124

Text #12

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9581. Min Act: -0.1700

Data Index: 4708270 (Open Web Text)

Max Activating Token Index: 662

Text #13

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9107. Min Act: -0.1700

Data Index: 8648986 (Open Web Text)

Max Activating Token Index: 89

Text #14

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9535. Min Act: -0.1700

Data Index: 2469995 (Open Web Text)

Max Activating Token Index: 484

Text #15

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9187. Min Act: -0.1700

Data Index: 6363126 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9624. Min Act: -0.1700

Data Index: 5463625 (Open Web Text)

Max Activating Token Index: 435

Text #17

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9138. Min Act: -0.1700

Data Index: 4232017 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.9115. Min Act: -0.1700

Data Index: 4546925 (Open Web Text)

Max Activating Token Index: 214

Text #19

Max Range: 6.1274. Min Range: -6.1274

Max Act: 5.8699. Min Act: -0.1700

Data Index: 3224445 (Open Web Text)

Max Activating Token Index: 710