Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 353 in Layer 15

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.1109. Min Act: -0.1700

Data Index: 6394893 (Open Web Text)

Max Activating Token Index: 262

Text #1

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0951. Min Act: -0.1700

Data Index: 717200 (Open Web Text)

Max Activating Token Index: 312

Text #2

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0162. Min Act: -0.1700

Data Index: 6002908 (Open Web Text)

Max Activating Token Index: 352

Text #3

Max Range: 3.1109. Min Range: -3.1109

Max Act: 3.0162. Min Act: -0.1700

Data Index: 1285918 (Open Web Text)

Max Activating Token Index: 802

Text #4

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9846. Min Act: -0.1700

Data Index: 6354572 (Open Web Text)

Max Activating Token Index: 656

Text #5

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9530. Min Act: -0.1700

Data Index: 8045111 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9371. Min Act: -0.1700

Data Index: 8428963 (Open Web Text)

Max Activating Token Index: 943

Text #7

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9371. Min Act: -0.1700

Data Index: 234662 (Open Web Text)

Max Activating Token Index: 786

Text #8

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9371. Min Act: -0.1700

Data Index: 8684569 (Open Web Text)

Max Activating Token Index: 441

Text #9

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9054. Min Act: -0.1700

Data Index: 1033755 (Open Web Text)

Max Activating Token Index: 994

Text #10

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9371. Min Act: -0.1700

Data Index: 131283 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9054. Min Act: -0.1700

Data Index: 8635569 (Open Web Text)

Max Activating Token Index: 20

Text #12

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8737. Min Act: -0.1700

Data Index: 1792076 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8896. Min Act: -0.1700

Data Index: 5055255 (Open Web Text)

Max Activating Token Index: 705

Text #14

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8896. Min Act: -0.1700

Data Index: 3189436 (Open Web Text)

Max Activating Token Index: 388

Text #15

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.9054. Min Act: -0.1700

Data Index: 4383423 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8896. Min Act: -0.1700

Data Index: 1133389 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8896. Min Act: -0.1700

Data Index: 3275804 (Open Web Text)

Max Activating Token Index: 666

Text #18

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8896. Min Act: -0.1700

Data Index: 630492 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 3.1109. Min Range: -3.1109

Max Act: 2.8578. Min Act: -0.1700

Data Index: 2895564 (Open Web Text)

Max Activating Token Index: 729