Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.1506. Min Act: -0.1700
Data Index: 368775 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.1194. Min Act: -0.1700
Data Index: 1049260 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 2724094 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 5143995 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0881. Min Act: -0.1700
Data Index: 1752922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 8657445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0569. Min Act: -0.1700
Data Index: 536809 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 18414 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 4007299 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 3505392 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 7563992 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 538718 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 2601436 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 3307576 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 6837172 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1506. Min Range: -4.1506
Max Act: 4.0256. Min Act: -0.1700
Data Index: 1537121 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1506. Min Range: -4.1506
Max Act: 3.9943. Min Act: -0.1700
Data Index: 3896999 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1506. Min Range: -4.1506
Max Act: 3.9943. Min Act: -0.1700
Data Index: 4015933 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1506. Min Range: -4.1506
Max Act: 3.9943. Min Act: -0.1700
Data Index: 2099514 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1506. Min Range: -4.1506
Max Act: 3.9943. Min Act: -0.1700
Data Index: 4159427 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19