Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6323. Min Range: -10.6323
Max Act: 10.6323. Min Act: -0.1700
Data Index: 504606 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6323. Min Range: -10.6323
Max Act: 10.1323. Min Act: -0.1700
Data Index: 5839235 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.9448. Min Act: -0.1700
Data Index: 2830867 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.9448. Min Act: -0.1700
Data Index: 1055256 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.8823. Min Act: -0.1700
Data Index: 5890760 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.8198. Min Act: -0.1700
Data Index: 6189819 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.8198. Min Act: -0.1700
Data Index: 5890736 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.7573. Min Act: -0.1700
Data Index: 7985445 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.6948. Min Act: -0.1700
Data Index: 4124049 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.6323. Min Act: -0.1700
Data Index: 5749703 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.6323. Min Act: -0.1700
Data Index: 8195855 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.5073. Min Act: -0.1700
Data Index: 5004859 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.5073. Min Act: -0.1700
Data Index: 3770855 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.5073. Min Act: -0.1700
Data Index: 82436 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.5073. Min Act: -0.1700
Data Index: 5890743 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.4448. Min Act: -0.1700
Data Index: 5468518 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.4448. Min Act: -0.1700
Data Index: 7948727 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.5073. Min Act: -0.1700
Data Index: 182110 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.3823. Min Act: -0.1700
Data Index: 5573400 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6323. Min Range: -10.6323
Max Act: 9.3823. Min Act: -0.1700
Data Index: 19961 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19