Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6127 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.8357. Min Act: -0.1700
Data Index: 1991874 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.3670. Min Act: -0.1700
Data Index: 251483 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.3670. Min Act: -0.1700
Data Index: 3972684 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.3357. Min Act: -0.1700
Data Index: 1710701 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.2732. Min Act: -0.1700
Data Index: 7955580 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.2107. Min Act: -0.1700
Data Index: 8740415 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.1482. Min Act: -0.1700
Data Index: 177112 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.1482. Min Act: -0.1700
Data Index: 3323483 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.0857. Min Act: -0.1700
Data Index: 1109693 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.0857. Min Act: -0.1700
Data Index: 3998729 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.0857. Min Act: -0.1700
Data Index: 4857571 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.0232. Min Act: -0.1700
Data Index: 7681419 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.0857. Min Act: -0.1700
Data Index: 702890 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8357. Min Range: -6.8357
Max Act: 6.0545. Min Act: -0.1700
Data Index: 1460166 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8357. Min Range: -6.8357
Max Act: 5.9607. Min Act: -0.1700
Data Index: 4188213 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8357. Min Range: -6.8357
Max Act: 5.9920. Min Act: -0.1700
Data Index: 7641427 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8357. Min Range: -6.8357
Max Act: 5.9607. Min Act: -0.1700
Data Index: 7683641 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8357. Min Range: -6.8357
Max Act: 5.9607. Min Act: -0.1700
Data Index: 7145297 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8357. Min Range: -6.8357
Max Act: 5.9295. Min Act: -0.1700
Data Index: 3068956 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8357. Min Range: -6.8357
Max Act: 5.9295. Min Act: -0.1700
Data Index: 5463330 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19