Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2191 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.7292. Min Act: -0.1700
Data Index: 7849744 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.5417. Min Act: -0.1700
Data Index: 6108631 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.3229. Min Act: -0.1700
Data Index: 7849743 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.2604. Min Act: -0.1700
Data Index: 4266499 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.2604. Min Act: -0.1700
Data Index: 2218985 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.2604. Min Act: -0.1700
Data Index: 5931285 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.1667. Min Act: -0.1700
Data Index: 2472330 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.1667. Min Act: -0.1700
Data Index: 1419821 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.1042. Min Act: -0.1700
Data Index: 3089803 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.0729. Min Act: -0.1700
Data Index: 6881861 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7292. Min Range: -7.7292
Max Act: 7.0104. Min Act: -0.1700
Data Index: 4550126 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7292. Min Range: -7.7292
Max Act: 6.9792. Min Act: -0.1700
Data Index: 6991100 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7292. Min Range: -7.7292
Max Act: 6.9792. Min Act: -0.1700
Data Index: 1572358 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7292. Min Range: -7.7292
Max Act: 6.9167. Min Act: -0.1700
Data Index: 8589195 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7292. Min Range: -7.7292
Max Act: 6.9479. Min Act: -0.1700
Data Index: 6881857 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7292. Min Range: -7.7292
Max Act: 6.9167. Min Act: -0.1700
Data Index: 453212 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7292. Min Range: -7.7292
Max Act: 6.8542. Min Act: -0.1700
Data Index: 1585915 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7292. Min Range: -7.7292
Max Act: 6.8854. Min Act: -0.1700
Data Index: 446785 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7292. Min Range: -7.7292
Max Act: 6.8229. Min Act: -0.1700
Data Index: 7664926 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7292. Min Range: -7.7292
Max Act: 6.7917. Min Act: -0.1700
Data Index: 5803532 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19