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

Dataset: Open Web Text

Neuron 2505 in Layer 1

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: 1.7665. Min Range: -1.7665

Max Act: 1.7660. Min Act: -0.1700

Data Index: 5384962 (Open Web Text)

Max Activating Token Index: 179

Text #1

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7665. Min Act: -0.1700

Data Index: 348732 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7634. Min Act: -0.1700

Data Index: 8444276 (Open Web Text)

Max Activating Token Index: 951

Text #3

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7643. Min Act: -0.1700

Data Index: 1883356 (Open Web Text)

Max Activating Token Index: 995

Text #4

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7526. Min Act: -0.1700

Data Index: 1320422 (Open Web Text)

Max Activating Token Index: 976

Text #5

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7591. Min Act: -0.1700

Data Index: 6299096 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7392. Min Act: -0.1700

Data Index: 3604866 (Open Web Text)

Max Activating Token Index: 301

Text #7

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7387. Min Act: -0.1700

Data Index: 6762161 (Open Web Text)

Max Activating Token Index: 292

Text #8

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7163. Min Act: -0.1700

Data Index: 1521260 (Open Web Text)

Max Activating Token Index: 873

Text #9

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7285. Min Act: -0.1700

Data Index: 3635965 (Open Web Text)

Max Activating Token Index: 207

Text #10

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7352. Min Act: -0.1700

Data Index: 2577170 (Open Web Text)

Max Activating Token Index: 455

Text #11

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7250. Min Act: -0.1700

Data Index: 3659872 (Open Web Text)

Max Activating Token Index: 594

Text #12

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7420. Min Act: -0.1700

Data Index: 1286194 (Open Web Text)

Max Activating Token Index: 690

Text #13

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7198. Min Act: -0.1700

Data Index: 3526626 (Open Web Text)

Max Activating Token Index: 524

Text #14

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7183. Min Act: -0.1700

Data Index: 7958395 (Open Web Text)

Max Activating Token Index: 248

Text #15

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7068. Min Act: -0.1700

Data Index: 2041701 (Open Web Text)

Max Activating Token Index: 982

Text #16

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7119. Min Act: -0.1700

Data Index: 8000098 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7091. Min Act: -0.1700

Data Index: 3002560 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7082. Min Act: -0.1700

Data Index: 6340396 (Open Web Text)

Max Activating Token Index: 172

Text #19

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7120. Min Act: -0.1700

Data Index: 7480703 (Open Web Text)

Max Activating Token Index: 316