Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3815 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7195. Min Range: -7.7195
Max Act: 7.7195. Min Act: -0.1700
Data Index: 8706766 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7195. Min Range: -7.7195
Max Act: 7.1882. Min Act: -0.1700
Data Index: 1555402 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7195. Min Range: -7.7195
Max Act: 7.1570. Min Act: -0.1700
Data Index: 7454914 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7195. Min Range: -7.7195
Max Act: 7.0320. Min Act: -0.1700
Data Index: 4239883 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7195. Min Range: -7.7195
Max Act: 7.0632. Min Act: -0.1700
Data Index: 8613414 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7195. Min Range: -7.7195
Max Act: 7.0632. Min Act: -0.1700
Data Index: 8519501 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7195. Min Range: -7.7195
Max Act: 7.0007. Min Act: -0.1700
Data Index: 3747849 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7195. Min Range: -7.7195
Max Act: 7.0007. Min Act: -0.1700
Data Index: 6774476 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7195. Min Range: -7.7195
Max Act: 7.0007. Min Act: -0.1700
Data Index: 7722005 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.9695. Min Act: -0.1700
Data Index: 8814673 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.9382. Min Act: -0.1700
Data Index: 8252147 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.9070. Min Act: -0.1700
Data Index: 1806144 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.8445. Min Act: -0.1700
Data Index: 1014924 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.8445. Min Act: -0.1700
Data Index: 2260959 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.7507. Min Act: -0.1700
Data Index: 466998 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.7820. Min Act: -0.1700
Data Index: 7983709 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.8132. Min Act: -0.1700
Data Index: 6324387 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.7507. Min Act: -0.1700
Data Index: 1040077 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.7195. Min Act: -0.1700
Data Index: 8679277 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7195. Min Range: -7.7195
Max Act: 6.6882. Min Act: -0.1700
Data Index: 818076 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19