Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4514 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3050. Min Range: -7.3050
Max Act: 7.3050. Min Act: -0.1700
Data Index: 2284194 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.9613. Min Act: -0.1699
Data Index: 6627896 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.8050. Min Act: -0.1687
Data Index: 2694147 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.7738. Min Act: -0.1699
Data Index: 2014102 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.7113. Min Act: -0.1700
Data Index: 5384980 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.7425. Min Act: -0.1700
Data Index: 1664770 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.7113. Min Act: -0.1685
Data Index: 1357938 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.7425. Min Act: -0.1700
Data Index: 389054 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.7113. Min Act: -0.1700
Data Index: 8282224 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.6488. Min Act: -0.1700
Data Index: 8282225 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.6175. Min Act: -0.1698
Data Index: 1418808 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.6488. Min Act: -0.1700
Data Index: 6081245 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.6175. Min Act: -0.1700
Data Index: 2444468 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.5863. Min Act: -0.1700
Data Index: 8802033 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.5550. Min Act: -0.1700
Data Index: 4651799 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.6175. Min Act: -0.1700
Data Index: 7269102 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.5238. Min Act: -0.1700
Data Index: 7563958 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.5550. Min Act: -0.1698
Data Index: 5334810 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.4925. Min Act: -0.1700
Data Index: 5216462 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3050. Min Range: -7.3050
Max Act: 6.4925. Min Act: -0.1700
Data Index: 158305 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19