Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 2447 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.1109. Min Act: -0.1700

Data Index: 8774120 (Open Web Text)

Max Activating Token Index: 885

Text #1

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.1109. Min Act: -0.1700

Data Index: 1576728 (Open Web Text)

Max Activating Token Index: 155

Text #2

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.0797. Min Act: -0.1700

Data Index: 3481232 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9547. Min Act: -0.1700

Data Index: 8171162 (Open Web Text)

Max Activating Token Index: 200

Text #4

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9547. Min Act: -0.1700

Data Index: 4569833 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9234. Min Act: -0.1700

Data Index: 5566994 (Open Web Text)

Max Activating Token Index: 221

Text #6

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8609. Min Act: -0.1700

Data Index: 7654873 (Open Web Text)

Max Activating Token Index: 706

Text #7

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8609. Min Act: -0.1700

Data Index: 5232294 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8297. Min Act: -0.1700

Data Index: 5337801 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7984. Min Act: -0.1700

Data Index: 8567165 (Open Web Text)

Max Activating Token Index: 269

Text #10

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7984. Min Act: -0.1700

Data Index: 6720531 (Open Web Text)

Max Activating Token Index: 449

Text #11

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8297. Min Act: -0.1700

Data Index: 7473483 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7984. Min Act: -0.1700

Data Index: 3411310 (Open Web Text)

Max Activating Token Index: 877

Text #13

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7359. Min Act: -0.1700

Data Index: 7659480 (Open Web Text)

Max Activating Token Index: 699

Text #14

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7672. Min Act: -0.1700

Data Index: 4808021 (Open Web Text)

Max Activating Token Index: 457

Text #15

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7672. Min Act: -0.1700

Data Index: 3171757 (Open Web Text)

Max Activating Token Index: 998

Text #16

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7672. Min Act: -0.1700

Data Index: 8289366 (Open Web Text)

Max Activating Token Index: 253

Text #17

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7672. Min Act: -0.1700

Data Index: 511982 (Open Web Text)

Max Activating Token Index: 768

Text #18

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7359. Min Act: -0.1700

Data Index: 7647127 (Open Web Text)

Max Activating Token Index: 717

Text #19

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7359. Min Act: -0.1700

Data Index: 2010837 (Open Web Text)

Max Activating Token Index: 734