Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.6992. Min Act: -0.1699
Data Index: 6534277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.6668. Min Act: -0.1700
Data Index: 1294609 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.6188. Min Act: -0.1649
Data Index: 4831714 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5873. Min Act: -0.1680
Data Index: 4460328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5873. Min Act: -0.1700
Data Index: 4477738 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5717. Min Act: -0.1700
Data Index: 1594821 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5562. Min Act: -0.1599
Data Index: 1452464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5562. Min Act: -0.1699
Data Index: 5824805 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5562. Min Act: -0.1700
Data Index: 870579 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5255. Min Act: -0.1700
Data Index: 7931383 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5255. Min Act: -0.1690
Data Index: 837142 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5562. Min Act: -0.1674
Data Index: 2173364 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5255. Min Act: -0.1699
Data Index: 1332313 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.4953. Min Act: -0.1698
Data Index: 8418441 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5103. Min Act: -0.1700
Data Index: 4477745 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.5103. Min Act: -0.1700
Data Index: 1147243 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.4953. Min Act: -0.1700
Data Index: 4477737 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.4804. Min Act: -0.1700
Data Index: 4477746 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.4804. Min Act: -0.1640
Data Index: 4733658 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6992. Min Range: -0.6992
Max Act: 0.4953. Min Act: -0.1687
Data Index: 1149935 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19