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

Dataset: Open Web Text

Neuron 617 in Layer 3

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: 4799133 (Open Web Text)

Max Activating Token Index: 375

Text #1

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.0484. Min Act: -0.1700

Data Index: 4656463 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.0484. Min Act: -0.1700

Data Index: 8739608 (Open Web Text)

Max Activating Token Index: 663

Text #3

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.0171. Min Act: -0.1700

Data Index: 2663165 (Open Web Text)

Max Activating Token Index: 492

Text #4

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9859. Min Act: -0.1700

Data Index: 1660676 (Open Web Text)

Max Activating Token Index: 399

Text #5

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9859. Min Act: -0.1700

Data Index: 7456829 (Open Web Text)

Max Activating Token Index: 475

Text #6

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9859. Min Act: -0.1700

Data Index: 5766219 (Open Web Text)

Max Activating Token Index: 457

Text #7

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9859. Min Act: -0.1700

Data Index: 5028255 (Open Web Text)

Max Activating Token Index: 746

Text #8

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9859. Min Act: -0.1700

Data Index: 8702741 (Open Web Text)

Max Activating Token Index: 186

Text #9

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 5123746 (Open Web Text)

Max Activating Token Index: 313

Text #10

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 324306 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 2530185 (Open Web Text)

Max Activating Token Index: 832

Text #12

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9234. Min Act: -0.1700

Data Index: 1013899 (Open Web Text)

Max Activating Token Index: 201

Text #13

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 4551213 (Open Web Text)

Max Activating Token Index: 690

Text #14

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9234. Min Act: -0.1700

Data Index: 6180695 (Open Web Text)

Max Activating Token Index: 222

Text #15

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9234. Min Act: -0.1700

Data Index: 7958543 (Open Web Text)

Max Activating Token Index: 285

Text #16

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8921. Min Act: -0.1700

Data Index: 3662911 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8921. Min Act: -0.1700

Data Index: 1044214 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8921. Min Act: -0.1700

Data Index: 5568368 (Open Web Text)

Max Activating Token Index: 455

Text #19

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8921. Min Act: -0.1700

Data Index: 3767661 (Open Web Text)

Max Activating Token Index: 480