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

Dataset: Open Web Text

Neuron 2719 in Layer 3

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: 8.1180. Min Range: -8.1180

Max Act: 8.1180. Min Act: -0.1700

Data Index: 1600574 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 8.1180. Min Range: -8.1180

Max Act: 8.0856. Min Act: -0.1700

Data Index: 1736923 (Open Web Text)

Max Activating Token Index: 572

Text #2

Max Range: 8.1180. Min Range: -8.1180

Max Act: 8.0426. Min Act: -0.1700

Data Index: 1259535 (Open Web Text)

Max Activating Token Index: 478

Text #3

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.8927. Min Act: -0.1700

Data Index: 2942433 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.9626. Min Act: -0.1700

Data Index: 4753022 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.8400. Min Act: -0.1700

Data Index: 3465648 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.9009. Min Act: -0.1700

Data Index: 7522137 (Open Web Text)

Max Activating Token Index: 533

Text #7

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.8319. Min Act: -0.1700

Data Index: 4234288 (Open Web Text)

Max Activating Token Index: 850

Text #8

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7967. Min Act: -0.1700

Data Index: 8473940 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7590. Min Act: -0.1700

Data Index: 1056466 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7867. Min Act: -0.1700

Data Index: 1931757 (Open Web Text)

Max Activating Token Index: 951

Text #11

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.8185. Min Act: -0.1700

Data Index: 7461554 (Open Web Text)

Max Activating Token Index: 922

Text #12

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7117. Min Act: -0.1700

Data Index: 4387083 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7413. Min Act: -0.1700

Data Index: 2087737 (Open Web Text)

Max Activating Token Index: 572

Text #14

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7367. Min Act: -0.1700

Data Index: 5154037 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7256. Min Act: -0.1700

Data Index: 1112288 (Open Web Text)

Max Activating Token Index: 776

Text #16

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7280. Min Act: -0.1700

Data Index: 1853790 (Open Web Text)

Max Activating Token Index: 720

Text #17

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.6898. Min Act: -0.1700

Data Index: 4119831 (Open Web Text)

Max Activating Token Index: 388

Text #18

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7280. Min Act: -0.1700

Data Index: 3854665 (Open Web Text)

Max Activating Token Index: 883

Text #19

Max Range: 8.1180. Min Range: -8.1180

Max Act: 7.7532. Min Act: -0.1700

Data Index: 252581 (Open Web Text)

Max Activating Token Index: 670