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

Dataset: Open Web Text

Neuron 2753 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: 3.1355. Min Range: -3.1355

Max Act: 3.1355. Min Act: -0.1700

Data Index: 6114976 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.9045. Min Act: -0.1700

Data Index: 6940582 (Open Web Text)

Max Activating Token Index: 193

Text #2

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.9038. Min Act: -0.1700

Data Index: 3279238 (Open Web Text)

Max Activating Token Index: 368

Text #3

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.8647. Min Act: -0.1700

Data Index: 6660968 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.8547. Min Act: -0.1700

Data Index: 2997092 (Open Web Text)

Max Activating Token Index: 262

Text #5

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.8370. Min Act: -0.1700

Data Index: 2635540 (Open Web Text)

Max Activating Token Index: 78

Text #6

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.8479. Min Act: -0.1700

Data Index: 5011127 (Open Web Text)

Max Activating Token Index: 986

Text #7

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.8624. Min Act: -0.1700

Data Index: 5397242 (Open Web Text)

Max Activating Token Index: 865

Text #8

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.8076. Min Act: -0.1700

Data Index: 334105 (Open Web Text)

Max Activating Token Index: 914

Text #9

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.8115. Min Act: -0.1700

Data Index: 1592783 (Open Web Text)

Max Activating Token Index: 172

Text #10

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.8053. Min Act: -0.1700

Data Index: 6985746 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.7800. Min Act: -0.1700

Data Index: 933194 (Open Web Text)

Max Activating Token Index: 417

Text #12

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.7856. Min Act: -0.1700

Data Index: 7236261 (Open Web Text)

Max Activating Token Index: 812

Text #13

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.7825. Min Act: -0.1700

Data Index: 4771298 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.7715. Min Act: -0.1700

Data Index: 1355625 (Open Web Text)

Max Activating Token Index: 573

Text #15

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.7872. Min Act: -0.1700

Data Index: 5375080 (Open Web Text)

Max Activating Token Index: 854

Text #16

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.7752. Min Act: -0.1700

Data Index: 5219884 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.7696. Min Act: -0.1700

Data Index: 4309095 (Open Web Text)

Max Activating Token Index: 511

Text #18

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.7724. Min Act: -0.1700

Data Index: 3780762 (Open Web Text)

Max Activating Token Index: 134

Text #19

Max Range: 3.1355. Min Range: -3.1355

Max Act: 2.7518. Min Act: -0.1700

Data Index: 7834272 (Open Web Text)

Max Activating Token Index: 529