Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2226 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0245. Min Range: -8.0245
Max Act: 8.0245. Min Act: -0.1700
Data Index: 2240171 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.9932. Min Act: -0.1700
Data Index: 2522627 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0245. Min Range: -8.0245
Max Act: 8.0245. Min Act: -0.1700
Data Index: 6534176 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.9620. Min Act: -0.1700
Data Index: 7011522 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.8370. Min Act: -0.1700
Data Index: 1784793 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.8370. Min Act: -0.1700
Data Index: 5583236 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.8057. Min Act: -0.1700
Data Index: 4101604 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.8370. Min Act: -0.1700
Data Index: 7320974 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.8057. Min Act: -0.1700
Data Index: 3125419 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.6807. Min Act: -0.1700
Data Index: 2938611 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.6807. Min Act: -0.1700
Data Index: 8803023 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.6495. Min Act: -0.1700
Data Index: 3117750 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.6495. Min Act: -0.1700
Data Index: 5987164 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.6182. Min Act: -0.1700
Data Index: 2913221 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.6182. Min Act: -0.1700
Data Index: 8341589 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.5245. Min Act: -0.1700
Data Index: 8254414 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.4932. Min Act: -0.1700
Data Index: 464328 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.4307. Min Act: -0.1700
Data Index: 4427220 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.4620. Min Act: -0.1700
Data Index: 4147857 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0245. Min Range: -8.0245
Max Act: 7.4620. Min Act: -0.1700
Data Index: 7506630 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19