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

Dataset: Open Web Text

Neuron 1352 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: 3.1152. Min Range: -3.1152

Max Act: 3.1152. Min Act: -0.1700

Data Index: 67234 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 3.1152. Min Range: -3.1152

Max Act: 3.0685. Min Act: -0.1700

Data Index: 8053281 (Open Web Text)

Max Activating Token Index: 511

Text #2

Max Range: 3.1152. Min Range: -3.1152

Max Act: 3.0284. Min Act: -0.1700

Data Index: 2994892 (Open Web Text)

Max Activating Token Index: 662

Text #3

Max Range: 3.1152. Min Range: -3.1152

Max Act: 3.0379. Min Act: -0.1700

Data Index: 4505887 (Open Web Text)

Max Activating Token Index: 890

Text #4

Max Range: 3.1152. Min Range: -3.1152

Max Act: 3.0226. Min Act: -0.1700

Data Index: 2223905 (Open Web Text)

Max Activating Token Index: 213

Text #5

Max Range: 3.1152. Min Range: -3.1152

Max Act: 3.0077. Min Act: -0.1700

Data Index: 5480083 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9974. Min Act: -0.1700

Data Index: 8574826 (Open Web Text)

Max Activating Token Index: 455

Text #7

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9713. Min Act: -0.1700

Data Index: 6905889 (Open Web Text)

Max Activating Token Index: 226

Text #8

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9567. Min Act: -0.1700

Data Index: 2890744 (Open Web Text)

Max Activating Token Index: 171

Text #9

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9830. Min Act: -0.1700

Data Index: 4858197 (Open Web Text)

Max Activating Token Index: 905

Text #10

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9733. Min Act: -0.1700

Data Index: 1345509 (Open Web Text)

Max Activating Token Index: 881

Text #11

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9683. Min Act: -0.1700

Data Index: 891869 (Open Web Text)

Max Activating Token Index: 788

Text #12

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9516. Min Act: -0.1700

Data Index: 4346665 (Open Web Text)

Max Activating Token Index: 118

Text #13

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9382. Min Act: -0.1700

Data Index: 7481180 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9640. Min Act: -0.1700

Data Index: 44309 (Open Web Text)

Max Activating Token Index: 892

Text #15

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9465. Min Act: -0.1700

Data Index: 1507228 (Open Web Text)

Max Activating Token Index: 524

Text #16

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9446. Min Act: -0.1700

Data Index: 6613569 (Open Web Text)

Max Activating Token Index: 472

Text #17

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9344. Min Act: -0.1700

Data Index: 998754 (Open Web Text)

Max Activating Token Index: 832

Text #18

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9485. Min Act: -0.1700

Data Index: 6640672 (Open Web Text)

Max Activating Token Index: 812

Text #19

Max Range: 3.1152. Min Range: -3.1152

Max Act: 2.9423. Min Act: -0.1700

Data Index: 4309052 (Open Web Text)

Max Activating Token Index: 620