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

Dataset: Open Web Text

Neuron 1861 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: 2.1012. Min Range: -2.1012

Max Act: 2.1012. Min Act: -0.1700

Data Index: 5868028 (Open Web Text)

Max Activating Token Index: 312

Text #1

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0362. Min Act: -0.1700

Data Index: 4425459 (Open Web Text)

Max Activating Token Index: 328

Text #2

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0118. Min Act: -0.1700

Data Index: 8357598 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0195. Min Act: -0.1700

Data Index: 8245377 (Open Web Text)

Max Activating Token Index: 362

Text #4

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0196. Min Act: -0.1700

Data Index: 3346203 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0209. Min Act: -0.1700

Data Index: 1801171 (Open Web Text)

Max Activating Token Index: 106

Text #6

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0002. Min Act: -0.1700

Data Index: 8082881 (Open Web Text)

Max Activating Token Index: 260

Text #7

Max Range: 2.1012. Min Range: -2.1012

Max Act: 1.9935. Min Act: -0.1700

Data Index: 4611010 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 2.1012. Min Range: -2.1012

Max Act: 1.9964. Min Act: -0.1700

Data Index: 1975799 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0043. Min Act: -0.1700

Data Index: 6132276 (Open Web Text)

Max Activating Token Index: 333

Text #10

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0098. Min Act: -0.1700

Data Index: 7736235 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0056. Min Act: -0.1700

Data Index: 7794588 (Open Web Text)

Max Activating Token Index: 658

Text #12

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0023. Min Act: -0.1700

Data Index: 1192211 (Open Web Text)

Max Activating Token Index: 288

Text #13

Max Range: 2.1012. Min Range: -2.1012

Max Act: 2.0064. Min Act: -0.1700

Data Index: 3164121 (Open Web Text)

Max Activating Token Index: 986

Text #14

Max Range: 2.1012. Min Range: -2.1012

Max Act: 1.9815. Min Act: -0.1700

Data Index: 8333009 (Open Web Text)

Max Activating Token Index: 235

Text #15

Max Range: 2.1012. Min Range: -2.1012

Max Act: 1.9849. Min Act: -0.1700

Data Index: 7734611 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.1012. Min Range: -2.1012

Max Act: 1.9874. Min Act: -0.1700

Data Index: 7514778 (Open Web Text)

Max Activating Token Index: 443

Text #17

Max Range: 2.1012. Min Range: -2.1012

Max Act: 1.9884. Min Act: -0.1700

Data Index: 4578566 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 2.1012. Min Range: -2.1012

Max Act: 1.9833. Min Act: -0.1700

Data Index: 3691254 (Open Web Text)

Max Activating Token Index: 596

Text #19

Max Range: 2.1012. Min Range: -2.1012

Max Act: 1.9798. Min Act: -0.1700

Data Index: 3558013 (Open Web Text)

Max Activating Token Index: 489