Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.6294. Min Act: -0.1700
Data Index: 5462337 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.3794. Min Act: -0.1700
Data Index: 2994960 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.2544. Min Act: -0.1700
Data Index: 5222886 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.1919. Min Act: -0.1700
Data Index: 5031673 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.1919. Min Act: -0.1700
Data Index: 633702 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.1294. Min Act: -0.1700
Data Index: 3826209 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.1294. Min Act: -0.1700
Data Index: 3096014 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0669. Min Act: -0.1700
Data Index: 5691406 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 3538953 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 7742284 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 5421590 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 1299586 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 6464804 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 7719601 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 8263490 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 5741486 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 5728401 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6294. Min Range: -8.6294
Max Act: 8.0044. Min Act: -0.1700
Data Index: 2041963 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6294. Min Range: -8.6294
Max Act: 7.9107. Min Act: -0.1700
Data Index: 7796479 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6294. Min Range: -8.6294
Max Act: 7.9107. Min Act: -0.1700
Data Index: 4607577 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19