Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0464. Min Range: -9.0464
Max Act: 9.0464. Min Act: -0.1700
Data Index: 177347 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0464. Min Range: -9.0464
Max Act: 8.6089. Min Act: -0.1700
Data Index: 8067372 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0464. Min Range: -9.0464
Max Act: 8.4839. Min Act: -0.1700
Data Index: 1600351 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0464. Min Range: -9.0464
Max Act: 8.4839. Min Act: -0.1700
Data Index: 3520778 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0464. Min Range: -9.0464
Max Act: 8.1714. Min Act: -0.1700
Data Index: 4140425 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0464. Min Range: -9.0464
Max Act: 8.0464. Min Act: -0.1700
Data Index: 965230 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0464. Min Range: -9.0464
Max Act: 8.0464. Min Act: -0.1700
Data Index: 5252574 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0464. Min Range: -9.0464
Max Act: 8.0464. Min Act: -0.1700
Data Index: 5333763 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0464. Min Range: -9.0464
Max Act: 8.0464. Min Act: -0.1700
Data Index: 5807174 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.9214. Min Act: -0.1700
Data Index: 4194565 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.9214. Min Act: -0.1700
Data Index: 4690134 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.9214. Min Act: -0.1700
Data Index: 73899 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.8589. Min Act: -0.1700
Data Index: 7221690 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.7964. Min Act: -0.1700
Data Index: 8678555 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.8589. Min Act: -0.1700
Data Index: 6499949 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.7964. Min Act: -0.1700
Data Index: 296145 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.7339. Min Act: -0.1700
Data Index: 3276434 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.7339. Min Act: -0.1700
Data Index: 8488193 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.7339. Min Act: -0.1700
Data Index: 2545785 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0464. Min Range: -9.0464
Max Act: 7.6714. Min Act: -0.1700
Data Index: 3847079 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19