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

Dataset: Open Web Text

Neuron 1785 in Layer 5

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: 3.0984. Min Range: -3.0984

Max Act: 3.0984. Min Act: -0.1700

Data Index: 6317600 (Open Web Text)

Max Activating Token Index: 772

Text #1

Max Range: 3.0984. Min Range: -3.0984

Max Act: 3.0205. Min Act: -0.1700

Data Index: 8329817 (Open Web Text)

Max Activating Token Index: 384

Text #2

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9736. Min Act: -0.1700

Data Index: 2917163 (Open Web Text)

Max Activating Token Index: 87

Text #3

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9306. Min Act: -0.1700

Data Index: 7081730 (Open Web Text)

Max Activating Token Index: 679

Text #4

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8805. Min Act: -0.1700

Data Index: 6814681 (Open Web Text)

Max Activating Token Index: 774

Text #5

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9199. Min Act: -0.1700

Data Index: 8382931 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9076. Min Act: -0.1700

Data Index: 1734487 (Open Web Text)

Max Activating Token Index: 136

Text #7

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.9240. Min Act: -0.1700

Data Index: 2908291 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8774. Min Act: -0.1700

Data Index: 2630850 (Open Web Text)

Max Activating Token Index: 375

Text #9

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8836. Min Act: -0.1700

Data Index: 1523442 (Open Web Text)

Max Activating Token Index: 384

Text #10

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8544. Min Act: -0.1700

Data Index: 2294427 (Open Web Text)

Max Activating Token Index: 922

Text #11

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8504. Min Act: -0.1700

Data Index: 6669097 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8308. Min Act: -0.1700

Data Index: 96852 (Open Web Text)

Max Activating Token Index: 389

Text #13

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8341. Min Act: -0.1700

Data Index: 6259603 (Open Web Text)

Max Activating Token Index: 357

Text #14

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8300. Min Act: -0.1700

Data Index: 2325084 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8403. Min Act: -0.1700

Data Index: 5419157 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8263. Min Act: -0.1700

Data Index: 3527229 (Open Web Text)

Max Activating Token Index: 530

Text #17

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8223. Min Act: -0.1700

Data Index: 4808116 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8443. Min Act: -0.1700

Data Index: 4048014 (Open Web Text)

Max Activating Token Index: 766

Text #19

Max Range: 3.0984. Min Range: -3.0984

Max Act: 2.8107. Min Act: -0.1700

Data Index: 919043 (Open Web Text)

Max Activating Token Index: 493