Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0835. Min Range: -4.0835
Max Act: 4.0835. Min Act: -0.1700
Data Index: 5887463 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0835. Min Range: -4.0835
Max Act: 4.0835. Min Act: -0.1700
Data Index: 7836932 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0835. Min Range: -4.0835
Max Act: 4.0835. Min Act: -0.1700
Data Index: 6902722 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0835. Min Range: -4.0835
Max Act: 4.0523. Min Act: -0.1700
Data Index: 6812034 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0835. Min Range: -4.0835
Max Act: 4.0523. Min Act: -0.1700
Data Index: 6902718 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0835. Min Range: -4.0835
Max Act: 4.0210. Min Act: -0.1700
Data Index: 6673274 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0835. Min Range: -4.0835
Max Act: 4.0210. Min Act: -0.1700
Data Index: 6882801 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9897. Min Act: -0.1700
Data Index: 3700126 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0835. Min Range: -4.0835
Max Act: 4.0210. Min Act: -0.1700
Data Index: 4522347 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9897. Min Act: -0.1700
Data Index: 8470980 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9897. Min Act: -0.1700
Data Index: 2598938 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9897. Min Act: -0.1700
Data Index: 4439532 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9897. Min Act: -0.1700
Data Index: 4370385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9897. Min Act: -0.1700
Data Index: 1634552 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9585. Min Act: -0.1700
Data Index: 1456616 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9585. Min Act: -0.1700
Data Index: 593914 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9585. Min Act: -0.1700
Data Index: 5960613 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9272. Min Act: -0.1700
Data Index: 8181965 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9585. Min Act: -0.1700
Data Index: 6091350 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0835. Min Range: -4.0835
Max Act: 3.9585. Min Act: -0.1700
Data Index: 1597850 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19