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

Dataset: Open Web Text

Neuron 2836 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: 1.9211. Min Range: -1.9211

Max Act: 1.9211. Min Act: -0.1700

Data Index: 7550424 (Open Web Text)

Max Activating Token Index: 761

Text #1

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.9058. Min Act: -0.1700

Data Index: 5458072 (Open Web Text)

Max Activating Token Index: 289

Text #2

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8254. Min Act: -0.1700

Data Index: 3942482 (Open Web Text)

Max Activating Token Index: 825

Text #3

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7728. Min Act: -0.1700

Data Index: 3217197 (Open Web Text)

Max Activating Token Index: 133

Text #4

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7490. Min Act: -0.1700

Data Index: 1803073 (Open Web Text)

Max Activating Token Index: 505

Text #5

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7816. Min Act: -0.1700

Data Index: 4570054 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7834. Min Act: -0.1700

Data Index: 8635192 (Open Web Text)

Max Activating Token Index: 288

Text #7

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7534. Min Act: -0.1700

Data Index: 8668642 (Open Web Text)

Max Activating Token Index: 69

Text #8

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7334. Min Act: -0.1700

Data Index: 5611326 (Open Web Text)

Max Activating Token Index: 318

Text #9

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7142. Min Act: -0.1700

Data Index: 4714828 (Open Web Text)

Max Activating Token Index: 980

Text #10

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7218. Min Act: -0.1699

Data Index: 7243351 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7230. Min Act: -0.1700

Data Index: 5917358 (Open Web Text)

Max Activating Token Index: 509

Text #12

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7378. Min Act: -0.1700

Data Index: 5812019 (Open Web Text)

Max Activating Token Index: 447

Text #13

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7316. Min Act: -0.1700

Data Index: 859045 (Open Web Text)

Max Activating Token Index: 141

Text #14

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7213. Min Act: -0.1700

Data Index: 7260787 (Open Web Text)

Max Activating Token Index: 883

Text #15

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7275. Min Act: -0.1698

Data Index: 127519 (Open Web Text)

Max Activating Token Index: 885

Text #16

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7049. Min Act: -0.1698

Data Index: 1880062 (Open Web Text)

Max Activating Token Index: 966

Text #17

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7069. Min Act: -0.1700

Data Index: 7322899 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7003. Min Act: -0.1700

Data Index: 4998862 (Open Web Text)

Max Activating Token Index: 936

Text #19

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7083. Min Act: -0.1700

Data Index: 3604241 (Open Web Text)

Max Activating Token Index: 87