Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4573 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.7828. Min Act: -0.1700
Data Index: 7340886 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6710. Min Act: -0.1700
Data Index: 4243381 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6710. Min Act: -0.1700
Data Index: 3399499 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6710. Min Act: -0.1700
Data Index: 5174640 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6549. Min Act: -0.1700
Data Index: 1448017 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6710. Min Act: -0.1700
Data Index: 5033483 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6549. Min Act: -0.1700
Data Index: 3709343 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6228. Min Act: -0.1700
Data Index: 7340887 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6228. Min Act: -0.1700
Data Index: 2449475 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6389. Min Act: -0.1700
Data Index: 3790217 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6228. Min Act: -0.1700
Data Index: 8575291 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6067. Min Act: -0.1700
Data Index: 2245776 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6067. Min Act: -0.1700
Data Index: 1109510 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6067. Min Act: -0.1700
Data Index: 8502265 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.6067. Min Act: -0.1700
Data Index: 7125758 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.5906. Min Act: -0.1700
Data Index: 3072600 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.5906. Min Act: -0.1700
Data Index: 161252 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.5906. Min Act: -0.1700
Data Index: 2068299 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.5745. Min Act: -0.1700
Data Index: 1448015 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7828. Min Range: -2.7828
Max Act: 2.5906. Min Act: -0.1700
Data Index: 6141149 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19