Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4099 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4974. Min Range: -7.4974
Max Act: 7.4974. Min Act: -0.1700
Data Index: 950082 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4974. Min Range: -7.4974
Max Act: 7.3724. Min Act: -0.1700
Data Index: 1412515 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4974. Min Range: -7.4974
Max Act: 7.1537. Min Act: -0.1700
Data Index: 3276626 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4974. Min Range: -7.4974
Max Act: 7.0912. Min Act: -0.1700
Data Index: 2761015 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4974. Min Range: -7.4974
Max Act: 7.0599. Min Act: -0.1700
Data Index: 6572316 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4974. Min Range: -7.4974
Max Act: 7.0599. Min Act: -0.1700
Data Index: 6623523 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4974. Min Range: -7.4974
Max Act: 7.0287. Min Act: -0.1700
Data Index: 2923088 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.9974. Min Act: -0.1700
Data Index: 5526738 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4974. Min Range: -7.4974
Max Act: 7.0287. Min Act: -0.1700
Data Index: 5237679 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.9974. Min Act: -0.1700
Data Index: 4874726 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.9974. Min Act: -0.1700
Data Index: 5523494 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.9662. Min Act: -0.1700
Data Index: 3137061 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.9349. Min Act: -0.1700
Data Index: 8121712 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.8724. Min Act: -0.1700
Data Index: 7284792 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.8724. Min Act: -0.1700
Data Index: 3587236 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.8412. Min Act: -0.1700
Data Index: 1845336 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.8412. Min Act: -0.1700
Data Index: 6472691 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.8412. Min Act: -0.1700
Data Index: 7509450 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.8412. Min Act: -0.1700
Data Index: 6343111 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4974. Min Range: -7.4974
Max Act: 6.8099. Min Act: -0.1700
Data Index: 221019 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19