Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.5419. Min Act: -0.1700
Data Index: 3546831 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.4482. Min Act: -0.1700
Data Index: 2601515 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.3857. Min Act: -0.1700
Data Index: 4258224 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.2919. Min Act: -0.1700
Data Index: 6720470 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.2919. Min Act: -0.1700
Data Index: 4989589 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.2294. Min Act: -0.1700
Data Index: 554856 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.2294. Min Act: -0.1700
Data Index: 4987588 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.1982. Min Act: -0.1700
Data Index: 4242375 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.1357. Min Act: -0.1700
Data Index: 2663438 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.1357. Min Act: -0.1700
Data Index: 1882381 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.1357. Min Act: -0.1700
Data Index: 1071036 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.1044. Min Act: -0.1700
Data Index: 1477301 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.1044. Min Act: -0.1700
Data Index: 4576206 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.0107. Min Act: -0.1700
Data Index: 4473969 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5419. Min Range: -7.5419
Max Act: 6.9794. Min Act: -0.1700
Data Index: 7844714 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5419. Min Range: -7.5419
Max Act: 7.0107. Min Act: -0.1700
Data Index: 2162154 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5419. Min Range: -7.5419
Max Act: 6.9794. Min Act: -0.1700
Data Index: 8546194 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5419. Min Range: -7.5419
Max Act: 6.9794. Min Act: -0.1700
Data Index: 51648 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5419. Min Range: -7.5419
Max Act: 6.9794. Min Act: -0.1700
Data Index: 4471713 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5419. Min Range: -7.5419
Max Act: 6.9169. Min Act: -0.1700
Data Index: 2769662 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19