Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3815 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2090. Min Range: -7.2090
Max Act: 7.2090. Min Act: -0.1700
Data Index: 2240133 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2090. Min Range: -7.2090
Max Act: 7.2090. Min Act: -0.1700
Data Index: 372856 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2090. Min Range: -7.2090
Max Act: 7.1465. Min Act: -0.1700
Data Index: 4003307 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2090. Min Range: -7.2090
Max Act: 7.1152. Min Act: -0.1700
Data Index: 1637304 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2090. Min Range: -7.2090
Max Act: 7.0840. Min Act: -0.1700
Data Index: 1636831 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2090. Min Range: -7.2090
Max Act: 7.0527. Min Act: -0.1700
Data Index: 3810686 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.9590. Min Act: -0.1700
Data Index: 2793295 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.9277. Min Act: -0.1700
Data Index: 2283897 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.8965. Min Act: -0.1700
Data Index: 3963498 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.8965. Min Act: -0.1700
Data Index: 1384144 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.8965. Min Act: -0.1700
Data Index: 8536269 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.8652. Min Act: -0.1700
Data Index: 2236305 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.8340. Min Act: -0.1700
Data Index: 2435588 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.8027. Min Act: -0.1700
Data Index: 2426455 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.8027. Min Act: -0.1700
Data Index: 3828507 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.8027. Min Act: -0.1700
Data Index: 5664531 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.7402. Min Act: -0.1700
Data Index: 1241705 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.7402. Min Act: -0.1700
Data Index: 3974576 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.7715. Min Act: -0.1700
Data Index: 4134559 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2090. Min Range: -7.2090
Max Act: 6.7402. Min Act: -0.1700
Data Index: 4087839 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19