Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5800 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3241. Min Range: -8.3241
Max Act: 8.3241. Min Act: -0.1700
Data Index: 754822 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3241. Min Range: -8.3241
Max Act: 8.1991. Min Act: -0.1700
Data Index: 7025500 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3241. Min Range: -8.3241
Max Act: 8.1366. Min Act: -0.1700
Data Index: 7806449 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3241. Min Range: -8.3241
Max Act: 8.0741. Min Act: -0.1700
Data Index: 5820965 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3241. Min Range: -8.3241
Max Act: 8.0116. Min Act: -0.1700
Data Index: 3823116 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.9491. Min Act: -0.1700
Data Index: 8061726 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.8866. Min Act: -0.1700
Data Index: 15613 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.8866. Min Act: -0.1700
Data Index: 3450721 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.8241. Min Act: -0.1700
Data Index: 4398189 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.8241. Min Act: -0.1700
Data Index: 127764 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.7616. Min Act: -0.1700
Data Index: 8620695 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.8241. Min Act: -0.1700
Data Index: 1910902 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.8241. Min Act: -0.1700
Data Index: 7961813 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.7616. Min Act: -0.1700
Data Index: 127743 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.7616. Min Act: -0.1700
Data Index: 6828788 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.6991. Min Act: -0.1700
Data Index: 3375454 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.6991. Min Act: -0.1700
Data Index: 7943392 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.6991. Min Act: -0.1700
Data Index: 6481641 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.6991. Min Act: -0.1700
Data Index: 5916168 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3241. Min Range: -8.3241
Max Act: 7.6991. Min Act: -0.1700
Data Index: 1529888 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19