Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2009 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.6863. Min Act: -0.1700
Data Index: 4288517 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.5613. Min Act: -0.1700
Data Index: 7555510 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.3113. Min Act: -0.1700
Data Index: 6120522 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.3113. Min Act: -0.1700
Data Index: 1951154 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.3113. Min Act: -0.1700
Data Index: 6866438 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.1863. Min Act: -0.1700
Data Index: 4594195 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.1551. Min Act: -0.1700
Data Index: 1263037 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.1551. Min Act: -0.1700
Data Index: 7374644 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.1238. Min Act: -0.1700
Data Index: 5353954 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.0926. Min Act: -0.1700
Data Index: 5353957 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.0613. Min Act: -0.1700
Data Index: 3326210 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6863. Min Range: -8.6863
Max Act: 8.0301. Min Act: -0.1700
Data Index: 3229904 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6863. Min Range: -8.6863
Max Act: 7.9676. Min Act: -0.1700
Data Index: 6496358 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6863. Min Range: -8.6863
Max Act: 7.9363. Min Act: -0.1700
Data Index: 5889415 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6863. Min Range: -8.6863
Max Act: 7.9051. Min Act: -0.1700
Data Index: 4468292 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6863. Min Range: -8.6863
Max Act: 7.8738. Min Act: -0.1700
Data Index: 2908080 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6863. Min Range: -8.6863
Max Act: 7.9051. Min Act: -0.1700
Data Index: 2867307 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6863. Min Range: -8.6863
Max Act: 7.9051. Min Act: -0.1700
Data Index: 6158615 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6863. Min Range: -8.6863
Max Act: 7.8738. Min Act: -0.1700
Data Index: 4022127 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6863. Min Range: -8.6863
Max Act: 7.8426. Min Act: -0.1700
Data Index: 1228008 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19