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

Dataset: Open Web Text

Neuron 1803 in Layer 2

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: 4.9339. Min Range: -4.9339

Max Act: 4.9339. Min Act: -0.1700

Data Index: 6068734 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.8324. Min Act: -0.1700

Data Index: 7544762 (Open Web Text)

Max Activating Token Index: 241

Text #2

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.7871. Min Act: -0.1700

Data Index: 1673346 (Open Web Text)

Max Activating Token Index: 317

Text #3

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.8006. Min Act: -0.1700

Data Index: 4151510 (Open Web Text)

Max Activating Token Index: 454

Text #4

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.7268. Min Act: -0.1700

Data Index: 3390890 (Open Web Text)

Max Activating Token Index: 554

Text #5

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.7155. Min Act: -0.1700

Data Index: 482782 (Open Web Text)

Max Activating Token Index: 743

Text #6

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.7093. Min Act: -0.1700

Data Index: 6098343 (Open Web Text)

Max Activating Token Index: 256

Text #7

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.7044. Min Act: -0.1700

Data Index: 4996324 (Open Web Text)

Max Activating Token Index: 401

Text #8

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.6985. Min Act: -0.1700

Data Index: 2655368 (Open Web Text)

Max Activating Token Index: 298

Text #9

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.6730. Min Act: -0.1700

Data Index: 7780348 (Open Web Text)

Max Activating Token Index: 257

Text #10

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.6888. Min Act: -0.1700

Data Index: 3837076 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.7227. Min Act: -0.1700

Data Index: 6292042 (Open Web Text)

Max Activating Token Index: 667

Text #12

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.6967. Min Act: -0.1700

Data Index: 1315823 (Open Web Text)

Max Activating Token Index: 434

Text #13

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.7213. Min Act: -0.1700

Data Index: 1739845 (Open Web Text)

Max Activating Token Index: 252

Text #14

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.6912. Min Act: -0.1700

Data Index: 2354253 (Open Web Text)

Max Activating Token Index: 284

Text #15

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.6542. Min Act: -0.1700

Data Index: 4412811 (Open Web Text)

Max Activating Token Index: 232

Text #16

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.6758. Min Act: -0.1700

Data Index: 5052400 (Open Web Text)

Max Activating Token Index: 447

Text #17

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.6548. Min Act: -0.1700

Data Index: 160836 (Open Web Text)

Max Activating Token Index: 621

Text #18

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.7067. Min Act: -0.1700

Data Index: 2659294 (Open Web Text)

Max Activating Token Index: 912

Text #19

Max Range: 4.9339. Min Range: -4.9339

Max Act: 4.6572. Min Act: -0.1700

Data Index: 5547080 (Open Web Text)

Max Activating Token Index: 443