Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.8822. Min Act: -0.1700
Data Index: 1315041 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.8510. Min Act: -0.1700
Data Index: 1275509 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.7885. Min Act: -0.1700
Data Index: 1194774 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.7260. Min Act: -0.1700
Data Index: 1612474 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.6635. Min Act: -0.1700
Data Index: 3845376 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.6322. Min Act: -0.1700
Data Index: 1070011 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.6322. Min Act: -0.1700
Data Index: 3035659 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.6010. Min Act: -0.1700
Data Index: 3469260 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5697. Min Act: -0.1700
Data Index: 1786846 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5385. Min Act: -0.1700
Data Index: 2299169 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5385. Min Act: -0.1700
Data Index: 2709098 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5385. Min Act: -0.1700
Data Index: 3460634 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5385. Min Act: -0.1700
Data Index: 1587933 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5385. Min Act: -0.1700
Data Index: 2394072 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5072. Min Act: -0.1700
Data Index: 8555826 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5072. Min Act: -0.1700
Data Index: 6316405 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5072. Min Act: -0.1700
Data Index: 4328213 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.5072. Min Act: -0.1700
Data Index: 1237062 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.4760. Min Act: -0.1700
Data Index: 6519041 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8822. Min Range: -4.8822
Max Act: 4.4760. Min Act: -0.1700
Data Index: 3591390 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19