Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4771 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.2601. Min Act: -0.1700
Data Index: 7124353 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.1976. Min Act: -0.1700
Data Index: 604174 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.1664. Min Act: -0.1700
Data Index: 916886 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.1351. Min Act: -0.1700
Data Index: 2231455 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.1351. Min Act: -0.1700
Data Index: 1241725 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.0726. Min Act: -0.1700
Data Index: 3397362 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.1039. Min Act: -0.1700
Data Index: 5504488 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.1039. Min Act: -0.1700
Data Index: 2374449 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.1039. Min Act: -0.1700
Data Index: 949237 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.0726. Min Act: -0.1700
Data Index: 7900469 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.0726. Min Act: -0.1700
Data Index: 3932053 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.0726. Min Act: -0.1700
Data Index: 8594755 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.0414. Min Act: -0.1700
Data Index: 4567842 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.0414. Min Act: -0.1700
Data Index: 7356938 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.0414. Min Act: -0.1700
Data Index: 1074306 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.0101. Min Act: -0.1700
Data Index: 6250365 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2601. Min Range: -5.2601
Max Act: 5.0101. Min Act: -0.1700
Data Index: 6250359 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2601. Min Range: -5.2601
Max Act: 4.9789. Min Act: -0.1700
Data Index: 7635737 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2601. Min Range: -5.2601
Max Act: 4.9789. Min Act: -0.1700
Data Index: 1230024 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2601. Min Range: -5.2601
Max Act: 4.9476. Min Act: -0.1700
Data Index: 5702142 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19