Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1392 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.6388. Min Act: -0.1700
Data Index: 7983371 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.3888. Min Act: -0.1700
Data Index: 4885480 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.3263. Min Act: -0.1700
Data Index: 2574003 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.2013. Min Act: -0.1700
Data Index: 5000476 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.2013. Min Act: -0.1700
Data Index: 3377916 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.1388. Min Act: -0.1700
Data Index: 8198015 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.1388. Min Act: -0.1700
Data Index: 4864593 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.1388. Min Act: -0.1700
Data Index: 3332295 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0763. Min Act: -0.1700
Data Index: 2313023 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0763. Min Act: -0.1700
Data Index: 8072280 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0763. Min Act: -0.1700
Data Index: 4656418 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0763. Min Act: -0.1700
Data Index: 277548 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0763. Min Act: -0.1700
Data Index: 7860718 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.1388. Min Act: -0.1700
Data Index: 3154395 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0763. Min Act: -0.1700
Data Index: 462369 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0138. Min Act: -0.1700
Data Index: 6531697 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0763. Min Act: -0.1700
Data Index: 2791097 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0763. Min Act: -0.1700
Data Index: 1739934 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0763. Min Act: -0.1700
Data Index: 3804874 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6388. Min Range: -10.6388
Max Act: 10.0138. Min Act: -0.1700
Data Index: 3815653 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19