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

Dataset: Open Web Text

Neuron 2295 in Layer 6

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: 3.0295. Min Range: -3.0295

Max Act: 3.0295. Min Act: -0.1700

Data Index: 1011726 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.8865. Min Act: -0.1700

Data Index: 6619275 (Open Web Text)

Max Activating Token Index: 187

Text #2

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.8276. Min Act: -0.1700

Data Index: 1304739 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7976. Min Act: -0.1700

Data Index: 5134311 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7665. Min Act: -0.1700

Data Index: 3106932 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7683. Min Act: -0.1700

Data Index: 1834988 (Open Web Text)

Max Activating Token Index: 227

Text #6

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7643. Min Act: -0.1700

Data Index: 4143305 (Open Web Text)

Max Activating Token Index: 660

Text #7

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7665. Min Act: -0.1700

Data Index: 4435758 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7566. Min Act: -0.1700

Data Index: 8479959 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7649. Min Act: -0.1700

Data Index: 1026349 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7418. Min Act: -0.1700

Data Index: 7542491 (Open Web Text)

Max Activating Token Index: 582

Text #11

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7256. Min Act: -0.1700

Data Index: 2941918 (Open Web Text)

Max Activating Token Index: 467

Text #12

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7418. Min Act: -0.1700

Data Index: 3705587 (Open Web Text)

Max Activating Token Index: 935

Text #13

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7220. Min Act: -0.1700

Data Index: 8616423 (Open Web Text)

Max Activating Token Index: 603

Text #14

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7324. Min Act: -0.1700

Data Index: 1785669 (Open Web Text)

Max Activating Token Index: 493

Text #15

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7141. Min Act: -0.1700

Data Index: 938084 (Open Web Text)

Max Activating Token Index: 233

Text #16

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7081. Min Act: -0.1700

Data Index: 3620055 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7251. Min Act: -0.1700

Data Index: 8369916 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7315. Min Act: -0.1700

Data Index: 2600381 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 3.0295. Min Range: -3.0295

Max Act: 2.7086. Min Act: -0.1700

Data Index: 4162271 (Open Web Text)

Max Activating Token Index: 864