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

Dataset: Open Web Text

Neuron 1141 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: 3.1178. Min Range: -3.1178

Max Act: 3.1178. Min Act: -0.1700

Data Index: 667880 (Open Web Text)

Max Activating Token Index: 360

Text #1

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.1095. Min Act: -0.1700

Data Index: 1081418 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.1113. Min Act: -0.1700

Data Index: 1210670 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.0716. Min Act: -0.1700

Data Index: 2413733 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.0623. Min Act: -0.1700

Data Index: 2083176 (Open Web Text)

Max Activating Token Index: 703

Text #5

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.0454. Min Act: -0.1700

Data Index: 8322510 (Open Web Text)

Max Activating Token Index: 443

Text #6

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.0367. Min Act: -0.1700

Data Index: 7588136 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.0397. Min Act: -0.1700

Data Index: 7094148 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.0170. Min Act: -0.1700

Data Index: 2192041 (Open Web Text)

Max Activating Token Index: 488

Text #9

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.0072. Min Act: -0.1700

Data Index: 2057131 (Open Web Text)

Max Activating Token Index: 207

Text #10

Max Range: 3.1178. Min Range: -3.1178

Max Act: 3.0082. Min Act: -0.1700

Data Index: 3910476 (Open Web Text)

Max Activating Token Index: 305

Text #11

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9792. Min Act: -0.1700

Data Index: 2932524 (Open Web Text)

Max Activating Token Index: 924

Text #12

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9906. Min Act: -0.1700

Data Index: 4540868 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9885. Min Act: -0.1700

Data Index: 2239199 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9654. Min Act: -0.1700

Data Index: 1478742 (Open Web Text)

Max Activating Token Index: 687

Text #15

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9761. Min Act: -0.1700

Data Index: 711994 (Open Web Text)

Max Activating Token Index: 303

Text #16

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9684. Min Act: -0.1700

Data Index: 3481480 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9827. Min Act: -0.1700

Data Index: 6941844 (Open Web Text)

Max Activating Token Index: 198

Text #18

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9582. Min Act: -0.1700

Data Index: 3252640 (Open Web Text)

Max Activating Token Index: 476

Text #19

Max Range: 3.1178. Min Range: -3.1178

Max Act: 2.9626. Min Act: -0.1700

Data Index: 3669134 (Open Web Text)

Max Activating Token Index: 639