Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4811 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2271. Min Range: -8.2271
Max Act: 8.2271. Min Act: -0.1700
Data Index: 2954991 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2271. Min Range: -8.2271
Max Act: 8.0709. Min Act: -0.1700
Data Index: 3061085 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.9459. Min Act: -0.1700
Data Index: 7597057 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.9146. Min Act: -0.1700
Data Index: 5062879 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.8834. Min Act: -0.1700
Data Index: 7073567 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.8834. Min Act: -0.1700
Data Index: 2590970 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.8834. Min Act: -0.1700
Data Index: 1287156 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.7896. Min Act: -0.1700
Data Index: 2613178 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6959. Min Act: -0.1700
Data Index: 6096421 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.7271. Min Act: -0.1700
Data Index: 8150918 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6959. Min Act: -0.1700
Data Index: 2301269 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6959. Min Act: -0.1700
Data Index: 4904096 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6646. Min Act: -0.1700
Data Index: 925474 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6646. Min Act: -0.1700
Data Index: 2384568 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6646. Min Act: -0.1700
Data Index: 3742321 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6646. Min Act: -0.1700
Data Index: 550474 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6334. Min Act: -0.1700
Data Index: 1808108 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6334. Min Act: -0.1700
Data Index: 294484 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.6334. Min Act: -0.1700
Data Index: 3100552 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2271. Min Range: -8.2271
Max Act: 7.5396. Min Act: -0.1700
Data Index: 4672390 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19