Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5381 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2312. Min Range: -6.2312
Max Act: 6.2312. Min Act: -0.1700
Data Index: 5000575 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.6062. Min Act: -0.1700
Data Index: 6551504 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.5749. Min Act: -0.1700
Data Index: 1638316 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.5124. Min Act: -0.1700
Data Index: 1624183 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.4499. Min Act: -0.1700
Data Index: 2531881 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.4499. Min Act: -0.1700
Data Index: 7224526 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.4187. Min Act: -0.1700
Data Index: 5776688 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3874. Min Act: -0.1700
Data Index: 5065984 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3874. Min Act: -0.1700
Data Index: 1391232 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3874. Min Act: -0.1700
Data Index: 8281230 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3874. Min Act: -0.1700
Data Index: 7731047 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3874. Min Act: -0.1700
Data Index: 475138 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3562. Min Act: -0.1700
Data Index: 1167966 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3562. Min Act: -0.1700
Data Index: 4883295 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3562. Min Act: -0.1700
Data Index: 6269320 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3562. Min Act: -0.1700
Data Index: 712136 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3562. Min Act: -0.1700
Data Index: 2016362 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3562. Min Act: -0.1700
Data Index: 4428573 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3249. Min Act: -0.1700
Data Index: 3918468 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2312. Min Range: -6.2312
Max Act: 5.3249. Min Act: -0.1700
Data Index: 7680397 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19