Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1963 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.5344. Min Act: -0.1700
Data Index: 1905285 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.3469. Min Act: -0.1700
Data Index: 5432641 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.3469. Min Act: -0.1700
Data Index: 6058743 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.3156. Min Act: -0.1700
Data Index: 3533620 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.2844. Min Act: -0.1700
Data Index: 886899 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.2219. Min Act: -0.1700
Data Index: 6216379 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.1906. Min Act: -0.1700
Data Index: 8484298 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.1906. Min Act: -0.1700
Data Index: 6968757 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.1906. Min Act: -0.1700
Data Index: 5259965 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.1594. Min Act: -0.1700
Data Index: 5742731 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.1594. Min Act: -0.1700
Data Index: 1288748 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.1594. Min Act: -0.1700
Data Index: 2360415 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.0969. Min Act: -0.1700
Data Index: 2493547 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.0656. Min Act: -0.1700
Data Index: 2065937 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.0031. Min Act: -0.1700
Data Index: 1677808 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.0031. Min Act: -0.1700
Data Index: 8097922 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.0031. Min Act: -0.1700
Data Index: 4451200 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5344. Min Range: -7.5344
Max Act: 7.0031. Min Act: -0.1700
Data Index: 6453589 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5344. Min Range: -7.5344
Max Act: 6.9719. Min Act: -0.1700
Data Index: 4254834 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5344. Min Range: -7.5344
Max Act: 6.9406. Min Act: -0.1700
Data Index: 7003438 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19