Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1058 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.4985. Min Act: -0.1700
Data Index: 271352 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.3110. Min Act: -0.1700
Data Index: 3483044 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.2798. Min Act: -0.1700
Data Index: 6482631 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.2173. Min Act: -0.1700
Data Index: 4736712 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.2485. Min Act: -0.1700
Data Index: 6279266 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.2173. Min Act: -0.1700
Data Index: 7517231 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.2173. Min Act: -0.1700
Data Index: 6000496 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.1548. Min Act: -0.1700
Data Index: 4014699 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.2173. Min Act: -0.1700
Data Index: 6701639 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.1548. Min Act: -0.1700
Data Index: 7427641 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0923. Min Act: -0.1700
Data Index: 7421999 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0610. Min Act: -0.1700
Data Index: 3932396 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0610. Min Act: -0.1700
Data Index: 7281614 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0610. Min Act: -0.1700
Data Index: 4098983 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0298. Min Act: -0.1700
Data Index: 5725513 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0298. Min Act: -0.1700
Data Index: 3172017 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0298. Min Act: -0.1700
Data Index: 5975520 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4985. Min Range: -6.4985
Max Act: 5.9985. Min Act: -0.1700
Data Index: 5853786 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4985. Min Range: -6.4985
Max Act: 5.9985. Min Act: -0.1700
Data Index: 2432367 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4985. Min Range: -6.4985
Max Act: 5.9985. Min Act: -0.1700
Data Index: 971137 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19