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

Dataset: Open Web Text

Neuron 770 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: 4.6055. Min Range: -4.6055

Max Act: 4.6055. Min Act: -0.1700

Data Index: 3933497 (Open Web Text)

Max Activating Token Index: 519

Text #1

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.5120. Min Act: -0.1700

Data Index: 2447986 (Open Web Text)

Max Activating Token Index: 571

Text #2

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.2409. Min Act: -0.1700

Data Index: 8580798 (Open Web Text)

Max Activating Token Index: 529

Text #3

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.1914. Min Act: -0.1700

Data Index: 664898 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.1535. Min Act: -0.1700

Data Index: 2110611 (Open Web Text)

Max Activating Token Index: 875

Text #5

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.1282. Min Act: -0.1700

Data Index: 6997723 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.1158. Min Act: -0.1700

Data Index: 8063658 (Open Web Text)

Max Activating Token Index: 689

Text #7

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.1068. Min Act: -0.1700

Data Index: 2354221 (Open Web Text)

Max Activating Token Index: 919

Text #8

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.1138. Min Act: -0.1700

Data Index: 7860081 (Open Web Text)

Max Activating Token Index: 139

Text #9

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0960. Min Act: -0.1700

Data Index: 3948097 (Open Web Text)

Max Activating Token Index: 614

Text #10

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0746. Min Act: -0.1700

Data Index: 4976277 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0838. Min Act: -0.1700

Data Index: 7358515 (Open Web Text)

Max Activating Token Index: 449

Text #12

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0717. Min Act: -0.1700

Data Index: 3671942 (Open Web Text)

Max Activating Token Index: 651

Text #13

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0708. Min Act: -0.1700

Data Index: 2010436 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0593. Min Act: -0.1700

Data Index: 3878674 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0557. Min Act: -0.1700

Data Index: 6378367 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0312. Min Act: -0.1700

Data Index: 3248117 (Open Web Text)

Max Activating Token Index: 992

Text #17

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0437. Min Act: -0.1700

Data Index: 6378363 (Open Web Text)

Max Activating Token Index: 97

Text #18

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0440. Min Act: -0.1700

Data Index: 2071657 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 4.6055. Min Range: -4.6055

Max Act: 4.0308. Min Act: -0.1700

Data Index: 2354222 (Open Web Text)

Max Activating Token Index: 726