Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.7147. Min Act: -0.1700
Data Index: 709704 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.7460. Min Act: -0.1700
Data Index: 2259589 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.7147. Min Act: -0.1700
Data Index: 6921839 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6835. Min Act: -0.1700
Data Index: 7305115 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6522. Min Act: -0.1700
Data Index: 7468039 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6522. Min Act: -0.1700
Data Index: 4279587 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6522. Min Act: -0.1700
Data Index: 3996678 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6210. Min Act: -0.1700
Data Index: 1837742 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6210. Min Act: -0.1700
Data Index: 2734340 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6210. Min Act: -0.1700
Data Index: 6305471 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6210. Min Act: -0.1700
Data Index: 5701199 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.6210. Min Act: -0.1700
Data Index: 2652998 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5897. Min Act: -0.1700
Data Index: 8153314 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5585. Min Act: -0.1700
Data Index: 3483268 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5897. Min Act: -0.1700
Data Index: 2017934 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5897. Min Act: -0.1700
Data Index: 257353 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5897. Min Act: -0.1700
Data Index: 3537880 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5585. Min Act: -0.1700
Data Index: 4742694 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5585. Min Act: -0.1700
Data Index: 5751081 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7460. Min Range: -6.7460
Max Act: 6.5585. Min Act: -0.1700
Data Index: 6305472 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19