Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1083 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3548. Min Range: -6.3548
Max Act: 6.3548. Min Act: -0.1700
Data Index: 6805014 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3548. Min Range: -6.3548
Max Act: 6.0423. Min Act: -0.1700
Data Index: 749421 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.9798. Min Act: -0.1700
Data Index: 6041667 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.9173. Min Act: -0.1700
Data Index: 4867947 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.8548. Min Act: -0.1700
Data Index: 180475 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.8235. Min Act: -0.1700
Data Index: 5278222 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.8235. Min Act: -0.1700
Data Index: 1167629 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.7923. Min Act: -0.1700
Data Index: 3628207 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.7298. Min Act: -0.1700
Data Index: 4259833 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.7610. Min Act: -0.1700
Data Index: 6056363 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.7298. Min Act: -0.1700
Data Index: 5320597 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.7298. Min Act: -0.1700
Data Index: 3469563 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.7298. Min Act: -0.1700
Data Index: 4627676 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.6985. Min Act: -0.1700
Data Index: 424446 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.6985. Min Act: -0.1700
Data Index: 2179467 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.6673. Min Act: -0.1700
Data Index: 1863291 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.6673. Min Act: -0.1700
Data Index: 3479533 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.6673. Min Act: -0.1700
Data Index: 1078214 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.6673. Min Act: -0.1700
Data Index: 3142925 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3548. Min Range: -6.3548
Max Act: 5.6673. Min Act: -0.1700
Data Index: 6135033 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19