Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1739. Min Range: -8.1739
Max Act: 8.1739. Min Act: -0.1700
Data Index: 1850914 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.6114. Min Act: -0.1700
Data Index: 4035304 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.4864. Min Act: -0.1700
Data Index: 2011685 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.4239. Min Act: -0.1700
Data Index: 474662 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.4239. Min Act: -0.1700
Data Index: 8357354 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.4239. Min Act: -0.1700
Data Index: 5374494 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.3614. Min Act: -0.1700
Data Index: 8084696 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.3927. Min Act: -0.1700
Data Index: 1132636 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.3927. Min Act: -0.1700
Data Index: 345291 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.3614. Min Act: -0.1700
Data Index: 837365 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.3614. Min Act: -0.1700
Data Index: 2277983 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.3302. Min Act: -0.1700
Data Index: 3479915 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.2989. Min Act: -0.1700
Data Index: 1574262 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.2989. Min Act: -0.1700
Data Index: 3940366 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.2989. Min Act: -0.1700
Data Index: 6550622 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.2989. Min Act: -0.1700
Data Index: 1993568 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.2677. Min Act: -0.1700
Data Index: 242578 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.2677. Min Act: -0.1700
Data Index: 1497685 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.2677. Min Act: -0.1700
Data Index: 3999854 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1739. Min Range: -8.1739
Max Act: 7.2364. Min Act: -0.1700
Data Index: 2620747 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19