Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4084 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.9988. Min Act: -0.1700
Data Index: 8634300 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.9676. Min Act: -0.1700
Data Index: 8335639 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.9051. Min Act: -0.1700
Data Index: 5845209 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.7801. Min Act: -0.1700
Data Index: 1560784 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.7488. Min Act: -0.1700
Data Index: 6841803 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.7176. Min Act: -0.1700
Data Index: 911768 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.7176. Min Act: -0.1700
Data Index: 1312776 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.6863. Min Act: -0.1700
Data Index: 930430 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.6238. Min Act: -0.1700
Data Index: 2088395 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5926. Min Act: -0.1700
Data Index: 5841169 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5926. Min Act: -0.1700
Data Index: 4823716 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5926. Min Act: -0.1700
Data Index: 1311030 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5613. Min Act: -0.1700
Data Index: 1829089 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5926. Min Act: -0.1700
Data Index: 114312 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5613. Min Act: -0.1700
Data Index: 8637489 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5613. Min Act: -0.1700
Data Index: 356605 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5613. Min Act: -0.1700
Data Index: 7101446 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5301. Min Act: -0.1700
Data Index: 6523384 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5301. Min Act: -0.1700
Data Index: 2726599 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9988. Min Range: -4.9988
Max Act: 4.5301. Min Act: -0.1700
Data Index: 7383851 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19