Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1997 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5770. Min Range: -8.5770
Max Act: 8.5770. Min Act: -0.1700
Data Index: 4332264 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5770. Min Range: -8.5770
Max Act: 8.1395. Min Act: -0.1700
Data Index: 654882 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5770. Min Range: -8.5770
Max Act: 8.1395. Min Act: -0.1700
Data Index: 7891492 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5770. Min Range: -8.5770
Max Act: 8.0770. Min Act: -0.1700
Data Index: 4068179 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5770. Min Range: -8.5770
Max Act: 8.0770. Min Act: -0.1700
Data Index: 5491268 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5770. Min Range: -8.5770
Max Act: 8.0145. Min Act: -0.1700
Data Index: 8772007 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5770. Min Range: -8.5770
Max Act: 8.0145. Min Act: -0.1700
Data Index: 4376009 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5770. Min Range: -8.5770
Max Act: 8.0145. Min Act: -0.1700
Data Index: 4547049 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5770. Min Range: -8.5770
Max Act: 8.0145. Min Act: -0.1700
Data Index: 4807863 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.9520. Min Act: -0.1700
Data Index: 1513185 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.9520. Min Act: -0.1700
Data Index: 4731004 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.8895. Min Act: -0.1700
Data Index: 4298218 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.8895. Min Act: -0.1700
Data Index: 1011959 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.8895. Min Act: -0.1700
Data Index: 4685857 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.7645. Min Act: -0.1700
Data Index: 6252340 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.7958. Min Act: -0.1700
Data Index: 1904218 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.7645. Min Act: -0.1700
Data Index: 642007 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.7645. Min Act: -0.1700
Data Index: 1400970 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.7333. Min Act: -0.1700
Data Index: 397936 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5770. Min Range: -8.5770
Max Act: 7.6708. Min Act: -0.1700
Data Index: 2525577 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19