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

Dataset: Open Web Text

Neuron 599 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: 1.8263. Min Range: -1.8263

Max Act: 1.8263. Min Act: -0.1700

Data Index: 6809786 (Open Web Text)

Max Activating Token Index: 871

Text #1

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.8078. Min Act: -0.1700

Data Index: 3424572 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7620. Min Act: -0.1700

Data Index: 7061144 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7490. Min Act: -0.1700

Data Index: 284693 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7442. Min Act: -0.1700

Data Index: 5231386 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7390. Min Act: -0.1700

Data Index: 1573968 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7385. Min Act: -0.1700

Data Index: 4998562 (Open Web Text)

Max Activating Token Index: 943

Text #7

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7325. Min Act: -0.1700

Data Index: 6125847 (Open Web Text)

Max Activating Token Index: 794

Text #8

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7431. Min Act: -0.1700

Data Index: 6429420 (Open Web Text)

Max Activating Token Index: 841

Text #9

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7365. Min Act: -0.1700

Data Index: 3034694 (Open Web Text)

Max Activating Token Index: 789

Text #10

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7089. Min Act: -0.1700

Data Index: 3790354 (Open Web Text)

Max Activating Token Index: 166

Text #11

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7152. Min Act: -0.1700

Data Index: 8460781 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7166. Min Act: -0.1700

Data Index: 3907232 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7203. Min Act: -0.1700

Data Index: 8614625 (Open Web Text)

Max Activating Token Index: 847

Text #14

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7140. Min Act: -0.1700

Data Index: 2412940 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7107. Min Act: -0.1700

Data Index: 6247290 (Open Web Text)

Max Activating Token Index: 856

Text #16

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7091. Min Act: -0.1700

Data Index: 7333907 (Open Web Text)

Max Activating Token Index: 307

Text #17

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.6927. Min Act: -0.1700

Data Index: 8604276 (Open Web Text)

Max Activating Token Index: 325

Text #18

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7007. Min Act: -0.1700

Data Index: 1212946 (Open Web Text)

Max Activating Token Index: 116

Text #19

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.6870. Min Act: -0.1700

Data Index: 765246 (Open Web Text)

Max Activating Token Index: 906