Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4809 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.1941. Min Act: -0.1700
Data Index: 1130010 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.1628. Min Act: -0.1700
Data Index: 3546614 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.1316. Min Act: -0.1700
Data Index: 5740779 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.1316. Min Act: -0.1700
Data Index: 2458269 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.1316. Min Act: -0.1700
Data Index: 306185 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.1003. Min Act: -0.1700
Data Index: 6308319 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.0378. Min Act: -0.1700
Data Index: 999027 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.0378. Min Act: -0.1700
Data Index: 3436718 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.0378. Min Act: -0.1700
Data Index: 7678391 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1941. Min Range: -4.1941
Max Act: 3.9753. Min Act: -0.1700
Data Index: 5181590 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.0066. Min Act: -0.1700
Data Index: 303915 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1941. Min Range: -4.1941
Max Act: 3.9753. Min Act: -0.1700
Data Index: 2261811 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1941. Min Range: -4.1941
Max Act: 3.9753. Min Act: -0.1700
Data Index: 1255043 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1941. Min Range: -4.1941
Max Act: 3.9753. Min Act: -0.1700
Data Index: 8701939 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1941. Min Range: -4.1941
Max Act: 3.9753. Min Act: -0.1700
Data Index: 5101600 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1941. Min Range: -4.1941
Max Act: 3.9440. Min Act: -0.1700
Data Index: 6128940 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1941. Min Range: -4.1941
Max Act: 4.0066. Min Act: -0.1700
Data Index: 5326649 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1941. Min Range: -4.1941
Max Act: 3.9440. Min Act: -0.1700
Data Index: 8426466 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1941. Min Range: -4.1941
Max Act: 3.9440. Min Act: -0.1700
Data Index: 7395059 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1941. Min Range: -4.1941
Max Act: 3.9440. Min Act: -0.1700
Data Index: 8426464 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19