Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 971 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0813. Min Range: -5.0813
Max Act: 5.0813. Min Act: -0.1547
Data Index: 1287399 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0813. Min Range: -5.0813
Max Act: 5.0813. Min Act: -0.1700
Data Index: 7277893 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0813. Min Range: -5.0813
Max Act: 5.0500. Min Act: -0.1700
Data Index: 8595427 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0813. Min Range: -5.0813
Max Act: 5.0188. Min Act: -0.1632
Data Index: 3491526 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.9563. Min Act: -0.1653
Data Index: 4762062 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.9250. Min Act: -0.1676
Data Index: 1245332 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.8938. Min Act: -0.1698
Data Index: 3491542 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.8938. Min Act: -0.1700
Data Index: 2222565 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.8625. Min Act: -0.1674
Data Index: 6787172 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.8625. Min Act: -0.1569
Data Index: 5272740 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.8313. Min Act: -0.1700
Data Index: 2320001 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.8000. Min Act: -0.1700
Data Index: 863076 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.7688. Min Act: -0.1700
Data Index: 1245336 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.7688. Min Act: -0.1700
Data Index: 6929174 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.7688. Min Act: -0.1700
Data Index: 486004 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.7063. Min Act: -0.1700
Data Index: 7223368 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.7375. Min Act: -0.1700
Data Index: 2534302 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.7375. Min Act: -0.1700
Data Index: 4762063 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.7375. Min Act: -0.1134
Data Index: 3491525 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0813. Min Range: -5.0813
Max Act: 4.7063. Min Act: -0.1700
Data Index: 4762061 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19