Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1605 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6993. Min Act: -0.1700
Data Index: 7605836 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6680. Min Act: -0.1700
Data Index: 7230313 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6680. Min Act: -0.1700
Data Index: 4824951 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6680. Min Act: -0.1700
Data Index: 7177845 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6368. Min Act: -0.1700
Data Index: 1997765 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6368. Min Act: -0.1700
Data Index: 610482 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6368. Min Act: -0.1700
Data Index: 7721903 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6368. Min Act: -0.1700
Data Index: 8006353 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6055. Min Act: -0.1700
Data Index: 8165585 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5743. Min Act: -0.1700
Data Index: 3585447 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5743. Min Act: -0.1700
Data Index: 7218589 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5743. Min Act: -0.1700
Data Index: 1804919 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5430. Min Act: -0.1700
Data Index: 5546943 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5430. Min Act: -0.1700
Data Index: 1930893 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5430. Min Act: -0.1700
Data Index: 5502176 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5118. Min Act: -0.1700
Data Index: 3030020 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5430. Min Act: -0.1700
Data Index: 701620 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5430. Min Act: -0.1700
Data Index: 39770 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5118. Min Act: -0.1700
Data Index: 7193906 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4805. Min Act: -0.1700
Data Index: 7901653 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19