Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.7846. Min Act: -0.1700
Data Index: 5281370 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.6567. Min Act: -0.1700
Data Index: 70511 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.6567. Min Act: -0.1700
Data Index: 3991909 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.6567. Min Act: -0.1700
Data Index: 70512 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.6407. Min Act: -0.1700
Data Index: 3720251 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.6407. Min Act: -0.1700
Data Index: 2319119 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.6407. Min Act: -0.1700
Data Index: 5226424 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.6085. Min Act: -0.1700
Data Index: 6656774 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5924. Min Act: -0.1700
Data Index: 2699858 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.6085. Min Act: -0.1700
Data Index: 36343 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5924. Min Act: -0.1700
Data Index: 3875121 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.6085. Min Act: -0.1700
Data Index: 6638167 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5763. Min Act: -0.1700
Data Index: 776977 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5924. Min Act: -0.1700
Data Index: 302688 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5602. Min Act: -0.1700
Data Index: 5416611 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5763. Min Act: -0.1700
Data Index: 7570845 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5763. Min Act: -0.1700
Data Index: 6437021 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5924. Min Act: -0.1700
Data Index: 5822218 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5763. Min Act: -0.1700
Data Index: 5322133 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7846. Min Range: -2.7846
Max Act: 2.5602. Min Act: -0.1700
Data Index: 70513 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19