Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.9492. Min Act: -0.1700
Data Index: 8523242 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.6679. Min Act: -0.1700
Data Index: 204004 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.6367. Min Act: -0.1700
Data Index: 355612 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.6054. Min Act: -0.1700
Data Index: 6489668 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.4804. Min Act: -0.1700
Data Index: 473257 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.4804. Min Act: -0.1700
Data Index: 8440216 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.4492. Min Act: -0.1700
Data Index: 3266072 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.4492. Min Act: -0.1700
Data Index: 2883227 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.4179. Min Act: -0.1700
Data Index: 3301343 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.4179. Min Act: -0.1700
Data Index: 2323848 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.3867. Min Act: -0.1700
Data Index: 587499 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.2617. Min Act: -0.1700
Data Index: 3386716 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.2617. Min Act: -0.1700
Data Index: 7363080 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.2617. Min Act: -0.1700
Data Index: 4547561 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.1992. Min Act: -0.1700
Data Index: 7689505 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.2617. Min Act: -0.1700
Data Index: 2521544 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.2304. Min Act: -0.1700
Data Index: 8422306 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.2304. Min Act: -0.1700
Data Index: 931348 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.2304. Min Act: -0.1700
Data Index: 7200715 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9492. Min Range: -6.9492
Max Act: 6.1992. Min Act: -0.1700
Data Index: 6652785 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19