Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1641 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.8973. Min Act: -0.1700
Data Index: 662643 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.8973. Min Act: -0.1700
Data Index: 4310978 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.8661. Min Act: -0.1700
Data Index: 1558168 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.8036. Min Act: -0.1700
Data Index: 7375815 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.7411. Min Act: -0.1700
Data Index: 7480305 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.7411. Min Act: -0.1700
Data Index: 6671669 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.7723. Min Act: -0.1700
Data Index: 258982 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.7098. Min Act: -0.1700
Data Index: 4945738 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.7098. Min Act: -0.1700
Data Index: 2631082 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.6161. Min Act: -0.1700
Data Index: 7002697 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.6473. Min Act: -0.1700
Data Index: 1162104 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.6473. Min Act: -0.1700
Data Index: 4595805 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.6161. Min Act: -0.1700
Data Index: 5707778 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.6161. Min Act: -0.1700
Data Index: 1043002 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.5848. Min Act: -0.1700
Data Index: 7846289 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.4911. Min Act: -0.1700
Data Index: 6347175 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.5223. Min Act: -0.1700
Data Index: 5788984 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.5223. Min Act: -0.1700
Data Index: 4714302 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.5223. Min Act: -0.1700
Data Index: 5442640 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8973. Min Range: -5.8973
Max Act: 5.4911. Min Act: -0.1700
Data Index: 4475721 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19