Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0312. Min Range: -5.0312
Max Act: 5.0312. Min Act: -0.1700
Data Index: 3157908 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9999. Min Act: -0.1700
Data Index: 6261768 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9999. Min Act: -0.1700
Data Index: 8280011 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9999. Min Act: -0.1700
Data Index: 3575307 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9687. Min Act: -0.1700
Data Index: 8684533 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9374. Min Act: -0.1700
Data Index: 8067805 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9374. Min Act: -0.1700
Data Index: 3030932 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9374. Min Act: -0.1700
Data Index: 694510 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9374. Min Act: -0.1700
Data Index: 1012747 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9374. Min Act: -0.1700
Data Index: 8290369 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9062. Min Act: -0.1700
Data Index: 5677901 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9062. Min Act: -0.1700
Data Index: 4097444 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9062. Min Act: -0.1700
Data Index: 5956355 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9062. Min Act: -0.1700
Data Index: 2345711 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9062. Min Act: -0.1700
Data Index: 6023771 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9062. Min Act: -0.1700
Data Index: 7585604 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.8749. Min Act: -0.1700
Data Index: 1033363 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.9062. Min Act: -0.1700
Data Index: 6697701 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.8749. Min Act: -0.1700
Data Index: 7492228 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0312. Min Range: -5.0312
Max Act: 4.8749. Min Act: -0.1700
Data Index: 5046090 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19