Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1069. Min Range: -12.1069
Max Act: 12.1069. Min Act: -0.1700
Data Index: 7485571 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.7319. Min Act: -0.1697
Data Index: 7588802 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.5444. Min Act: -0.1700
Data Index: 1585020 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.4819. Min Act: -0.1700
Data Index: 8127727 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.3569. Min Act: -0.1700
Data Index: 5909290 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.2944. Min Act: -0.1699
Data Index: 7613068 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.2944. Min Act: -0.1700
Data Index: 5615665 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.2319. Min Act: -0.1699
Data Index: 5992249 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.2319. Min Act: -0.1699
Data Index: 2169520 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.1694. Min Act: -0.1700
Data Index: 6558861 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.1694. Min Act: -0.1698
Data Index: 4772913 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.1694. Min Act: -0.1700
Data Index: 1370947 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.1069. Min Act: -0.1698
Data Index: 1376761 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.1069. Min Act: -0.1700
Data Index: 5630560 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.1069. Min Act: -0.1700
Data Index: 7795685 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.1069. Min Act: -0.1699
Data Index: 7904624 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.1069. Min Act: -0.1700
Data Index: 4696536 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.0444. Min Act: -0.1700
Data Index: 4087593 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.0444. Min Act: -0.1700
Data Index: 5299768 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1069. Min Range: -12.1069
Max Act: 11.0444. Min Act: -0.1700
Data Index: 304728 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19