Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.9753. Min Act: -0.1700
Data Index: 1097429 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.8191. Min Act: -0.1700
Data Index: 4052547 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.7566. Min Act: -0.1700
Data Index: 4205498 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.6941. Min Act: -0.1700
Data Index: 6966313 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.6316. Min Act: -0.1700
Data Index: 892228 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.6003. Min Act: -0.1700
Data Index: 4046305 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.5691. Min Act: -0.1700
Data Index: 1369845 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.5378. Min Act: -0.1700
Data Index: 8722033 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.5691. Min Act: -0.1700
Data Index: 7072859 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.5378. Min Act: -0.1700
Data Index: 4770582 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.5066. Min Act: -0.1700
Data Index: 4232826 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.5066. Min Act: -0.1700
Data Index: 7327681 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.4753. Min Act: -0.1700
Data Index: 4169588 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.4441. Min Act: -0.1700
Data Index: 7279527 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.4441. Min Act: -0.1700
Data Index: 7685805 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.4128. Min Act: -0.1700
Data Index: 4578403 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.4441. Min Act: -0.1700
Data Index: 8812601 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.3816. Min Act: -0.1700
Data Index: 7141104 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.4128. Min Act: -0.1700
Data Index: 1163488 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9753. Min Range: -6.9753
Max Act: 6.4128. Min Act: -0.1700
Data Index: 2034325 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19