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

Dataset: Open Web Text

Neuron 1216 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: 3.6157. Min Range: -3.6157

Max Act: 3.6157. Min Act: -0.1700

Data Index: 6134184 (Open Web Text)

Max Activating Token Index: 524

Text #1

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.4307. Min Act: -0.1700

Data Index: 3272959 (Open Web Text)

Max Activating Token Index: 936

Text #2

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.4291. Min Act: -0.1700

Data Index: 6216807 (Open Web Text)

Max Activating Token Index: 619

Text #3

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.4430. Min Act: -0.1700

Data Index: 2842860 (Open Web Text)

Max Activating Token Index: 967

Text #4

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.4084. Min Act: -0.1700

Data Index: 1649043 (Open Web Text)

Max Activating Token Index: 868

Text #5

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.4227. Min Act: -0.1700

Data Index: 4845411 (Open Web Text)

Max Activating Token Index: 423

Text #6

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.4218. Min Act: -0.1700

Data Index: 6952603 (Open Web Text)

Max Activating Token Index: 504

Text #7

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.4159. Min Act: -0.1700

Data Index: 1693133 (Open Web Text)

Max Activating Token Index: 726

Text #8

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.4083. Min Act: -0.1700

Data Index: 3115458 (Open Web Text)

Max Activating Token Index: 945

Text #9

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3946. Min Act: -0.1700

Data Index: 316170 (Open Web Text)

Max Activating Token Index: 228

Text #10

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3983. Min Act: -0.1700

Data Index: 4991210 (Open Web Text)

Max Activating Token Index: 506

Text #11

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3875. Min Act: -0.1700

Data Index: 4618022 (Open Web Text)

Max Activating Token Index: 145

Text #12

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3861. Min Act: -0.1700

Data Index: 6701727 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3923. Min Act: -0.1700

Data Index: 6440995 (Open Web Text)

Max Activating Token Index: 464

Text #14

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3839. Min Act: -0.1700

Data Index: 8457121 (Open Web Text)

Max Activating Token Index: 712

Text #15

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3795. Min Act: -0.1700

Data Index: 3067562 (Open Web Text)

Max Activating Token Index: 395

Text #16

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3873. Min Act: -0.1700

Data Index: 3825141 (Open Web Text)

Max Activating Token Index: 452

Text #17

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3831. Min Act: -0.1700

Data Index: 5617362 (Open Web Text)

Max Activating Token Index: 825

Text #18

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3768. Min Act: -0.1700

Data Index: 744393 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 3.6157. Min Range: -3.6157

Max Act: 3.3645. Min Act: -0.1700

Data Index: 1389579 (Open Web Text)

Max Activating Token Index: 914