Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1535 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0050. Min Range: -4.0050
Max Act: 4.0050. Min Act: -0.1700
Data Index: 6888325 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.8174. Min Act: -0.1700
Data Index: 8062948 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.8174. Min Act: -0.1700
Data Index: 2927137 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.7862. Min Act: -0.1700
Data Index: 1427985 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.7549. Min Act: -0.1700
Data Index: 256989 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.7236. Min Act: -0.1700
Data Index: 4922640 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6923. Min Act: -0.1700
Data Index: 2263041 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6923. Min Act: -0.1700
Data Index: 7360290 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6923. Min Act: -0.1700
Data Index: 8008593 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6767. Min Act: -0.1700
Data Index: 8299598 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6767. Min Act: -0.1700
Data Index: 7118188 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6767. Min Act: -0.1700
Data Index: 6827983 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6767. Min Act: -0.1700
Data Index: 3616522 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6610. Min Act: -0.1700
Data Index: 6397328 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6610. Min Act: -0.1700
Data Index: 6423028 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6610. Min Act: -0.1700
Data Index: 3915221 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6454. Min Act: -0.1700
Data Index: 6711931 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6610. Min Act: -0.1700
Data Index: 4490036 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6454. Min Act: -0.1700
Data Index: 5093995 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0050. Min Range: -4.0050
Max Act: 3.6141. Min Act: -0.1700
Data Index: 3149365 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19