Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0468. Min Range: -10.0468
Max Act: 10.0468. Min Act: -0.1700
Data Index: 5794001 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.9843. Min Act: -0.1700
Data Index: 2761421 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.7968. Min Act: -0.1700
Data Index: 316304 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.7968. Min Act: -0.1700
Data Index: 2241955 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.6718. Min Act: -0.1700
Data Index: 6544629 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.6718. Min Act: -0.1700
Data Index: 6462740 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.6093. Min Act: -0.1700
Data Index: 1957219 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.5468. Min Act: -0.1700
Data Index: 6645277 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.4843. Min Act: -0.1700
Data Index: 1789721 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.4843. Min Act: -0.1700
Data Index: 804021 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.4843. Min Act: -0.1700
Data Index: 2070339 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.4843. Min Act: -0.1700
Data Index: 7815832 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.4843. Min Act: -0.1700
Data Index: 3325531 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.4218. Min Act: -0.1700
Data Index: 7222796 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.3593. Min Act: -0.1700
Data Index: 5615504 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.3593. Min Act: -0.1700
Data Index: 2476963 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.3593. Min Act: -0.1700
Data Index: 3931664 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.3593. Min Act: -0.1700
Data Index: 3454162 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.2968. Min Act: -0.1700
Data Index: 1435481 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0468. Min Range: -10.0468
Max Act: 9.3593. Min Act: -0.1700
Data Index: 5363755 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19