Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1911 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.8382. Min Act: -0.1700
Data Index: 689488 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.7757. Min Act: -0.1700
Data Index: 7967485 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.5257. Min Act: -0.1700
Data Index: 1859052 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.5257. Min Act: -0.1700
Data Index: 7374151 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.4632. Min Act: -0.1700
Data Index: 4226425 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.3382. Min Act: -0.1700
Data Index: 4953349 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.3382. Min Act: -0.1700
Data Index: 3447077 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.3382. Min Act: -0.1700
Data Index: 1006214 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.3382. Min Act: -0.1700
Data Index: 488635 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.2757. Min Act: -0.1700
Data Index: 5255863 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.2757. Min Act: -0.1700
Data Index: 1816386 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.3382. Min Act: -0.1700
Data Index: 1608772 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.2132. Min Act: -0.1700
Data Index: 1006213 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.2132. Min Act: -0.1700
Data Index: 7220704 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.2132. Min Act: -0.1700
Data Index: 8111103 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.1507. Min Act: -0.1700
Data Index: 6154887 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.0882. Min Act: -0.1700
Data Index: 5199312 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.1507. Min Act: -0.1700
Data Index: 6722603 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.1507. Min Act: -0.1700
Data Index: 6991575 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8382. Min Range: -12.8382
Max Act: 12.0882. Min Act: -0.1700
Data Index: 913436 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19