Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 488 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5245. Min Range: -6.5245
Max Act: 6.5245. Min Act: -0.1700
Data Index: 7983305 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5245. Min Range: -6.5245
Max Act: 6.4308. Min Act: -0.1700
Data Index: 2794517 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5245. Min Range: -6.5245
Max Act: 6.3058. Min Act: -0.1700
Data Index: 1402824 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5245. Min Range: -6.5245
Max Act: 6.2745. Min Act: -0.1700
Data Index: 2661854 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5245. Min Range: -6.5245
Max Act: 6.2745. Min Act: -0.1700
Data Index: 5358097 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5245. Min Range: -6.5245
Max Act: 6.1495. Min Act: -0.1700
Data Index: 4895316 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5245. Min Range: -6.5245
Max Act: 6.1183. Min Act: -0.1700
Data Index: 1530677 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.9933. Min Act: -0.1700
Data Index: 3678670 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.9933. Min Act: -0.1700
Data Index: 6546886 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.9620. Min Act: -0.1700
Data Index: 3878000 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.9620. Min Act: -0.1700
Data Index: 2304894 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.9308. Min Act: -0.1700
Data Index: 5428548 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.9308. Min Act: -0.1700
Data Index: 6207131 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.8995. Min Act: -0.1700
Data Index: 6603834 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.8995. Min Act: -0.1700
Data Index: 6668726 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.8683. Min Act: -0.1700
Data Index: 2333698 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.8683. Min Act: -0.1700
Data Index: 7434982 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.8683. Min Act: -0.1700
Data Index: 3751036 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.8370. Min Act: -0.1700
Data Index: 7469481 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5245. Min Range: -6.5245
Max Act: 5.8370. Min Act: -0.1700
Data Index: 7013735 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19