Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.6110. Min Act: -0.1700
Data Index: 1518185 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.6110. Min Act: -0.1700
Data Index: 3069546 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.2985. Min Act: -0.1700
Data Index: 8350414 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.3297. Min Act: -0.1700
Data Index: 5682141 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1735. Min Act: -0.1700
Data Index: 6590393 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1422. Min Act: -0.1700
Data Index: 6870172 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 2031624 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 3355091 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 4414101 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 2174925 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 3661669 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 6182230 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1552085 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1379070 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0797. Min Act: -0.1700
Data Index: 8046534 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1166062 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0485. Min Act: -0.1700
Data Index: 6918577 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0485. Min Act: -0.1700
Data Index: 4346108 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0485. Min Act: -0.1700
Data Index: 6155881 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6110. Min Range: -5.6110
Max Act: 5.0485. Min Act: -0.1700
Data Index: 4609022 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19