Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1895. Min Range: -6.1895
Max Act: 6.1895. Min Act: -0.1700
Data Index: 5095009 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.8770. Min Act: -0.1700
Data Index: 3846097 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.8770. Min Act: -0.1700
Data Index: 5779965 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.8458. Min Act: -0.1700
Data Index: 2504427 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.7520. Min Act: -0.1700
Data Index: 2715195 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.7520. Min Act: -0.1700
Data Index: 502692 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.7520. Min Act: -0.1700
Data Index: 2498212 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.6583. Min Act: -0.1700
Data Index: 1716542 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.6583. Min Act: -0.1700
Data Index: 7261536 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.6583. Min Act: -0.1700
Data Index: 6973220 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.6583. Min Act: -0.1700
Data Index: 6697154 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.5958. Min Act: -0.1700
Data Index: 1435098 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.5958. Min Act: -0.1700
Data Index: 6822760 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.5645. Min Act: -0.1700
Data Index: 3163036 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.5645. Min Act: -0.1700
Data Index: 1851639 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.5645. Min Act: -0.1700
Data Index: 6476147 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.5333. Min Act: -0.1700
Data Index: 1932931 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.5333. Min Act: -0.1700
Data Index: 8236476 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.5020. Min Act: -0.1700
Data Index: 1153760 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1895. Min Range: -6.1895
Max Act: 5.5020. Min Act: -0.1700
Data Index: 1019674 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19