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

Dataset: Open Web Text

Neuron 562 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: 4.1185. Min Range: -4.1185

Max Act: 4.1185. Min Act: -0.1700

Data Index: 3337117 (Open Web Text)

Max Activating Token Index: 264

Text #1

Max Range: 4.1185. Min Range: -4.1185

Max Act: 4.0731. Min Act: -0.1700

Data Index: 6047380 (Open Web Text)

Max Activating Token Index: 940

Text #2

Max Range: 4.1185. Min Range: -4.1185

Max Act: 4.0368. Min Act: -0.1700

Data Index: 8587620 (Open Web Text)

Max Activating Token Index: 546

Text #3

Max Range: 4.1185. Min Range: -4.1185

Max Act: 4.0638. Min Act: -0.1700

Data Index: 46343 (Open Web Text)

Max Activating Token Index: 845

Text #4

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9847. Min Act: -0.1700

Data Index: 2463031 (Open Web Text)

Max Activating Token Index: 204

Text #5

Max Range: 4.1185. Min Range: -4.1185

Max Act: 4.0058. Min Act: -0.1700

Data Index: 7579799 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9464. Min Act: -0.1700

Data Index: 4261595 (Open Web Text)

Max Activating Token Index: 303

Text #7

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9384. Min Act: -0.1700

Data Index: 4117960 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9674. Min Act: -0.1700

Data Index: 1929883 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9333. Min Act: -0.1700

Data Index: 6656034 (Open Web Text)

Max Activating Token Index: 262

Text #10

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9678. Min Act: -0.1700

Data Index: 3103343 (Open Web Text)

Max Activating Token Index: 197

Text #11

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9500. Min Act: -0.1700

Data Index: 1597366 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9396. Min Act: -0.1700

Data Index: 4928533 (Open Web Text)

Max Activating Token Index: 594

Text #13

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9433. Min Act: -0.1700

Data Index: 6556445 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9427. Min Act: -0.1700

Data Index: 2047901 (Open Web Text)

Max Activating Token Index: 259

Text #15

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9508. Min Act: -0.1700

Data Index: 4920295 (Open Web Text)

Max Activating Token Index: 629

Text #16

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9181. Min Act: -0.1700

Data Index: 7309472 (Open Web Text)

Max Activating Token Index: 369

Text #17

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9738. Min Act: -0.1700

Data Index: 4135199 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.8964. Min Act: -0.1700

Data Index: 4682300 (Open Web Text)

Max Activating Token Index: 506

Text #19

Max Range: 4.1185. Min Range: -4.1185

Max Act: 3.9764. Min Act: -0.1700

Data Index: 2937292 (Open Web Text)

Max Activating Token Index: 46