Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3030 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5735. Min Range: -9.5735
Max Act: 9.5735. Min Act: -0.1700
Data Index: 3972375 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.9485. Min Act: -0.1700
Data Index: 3838814 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.8235. Min Act: -0.1700
Data Index: 4601933 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.7610. Min Act: -0.1700
Data Index: 2487555 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.6985. Min Act: -0.1700
Data Index: 7221587 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.5735. Min Act: -0.1700
Data Index: 7326788 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.5110. Min Act: -0.1700
Data Index: 3972376 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.4485. Min Act: -0.1700
Data Index: 337711 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.4485. Min Act: -0.1700
Data Index: 3489134 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.3860. Min Act: -0.1700
Data Index: 6641780 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.3235. Min Act: -0.1700
Data Index: 3780121 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.2610. Min Act: -0.1700
Data Index: 4090315 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.1047. Min Act: -0.1700
Data Index: 523213 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.0422. Min Act: -0.1700
Data Index: 3844313 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.0110. Min Act: -0.1700
Data Index: 8000061 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5735. Min Range: -9.5735
Max Act: 8.0110. Min Act: -0.1700
Data Index: 6909777 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5735. Min Range: -9.5735
Max Act: 7.9485. Min Act: -0.1700
Data Index: 7645712 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5735. Min Range: -9.5735
Max Act: 7.9172. Min Act: -0.1700
Data Index: 5198374 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5735. Min Range: -9.5735
Max Act: 7.9485. Min Act: -0.1700
Data Index: 6720569 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5735. Min Range: -9.5735
Max Act: 7.9485. Min Act: -0.1700
Data Index: 8018273 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19