Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4130 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4083. Min Range: -8.4083
Max Act: 8.4083. Min Act: -0.1700
Data Index: 4563803 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4083. Min Range: -8.4083
Max Act: 8.1583. Min Act: -0.1700
Data Index: 5830696 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.8458. Min Act: -0.1700
Data Index: 3961920 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.8145. Min Act: -0.1700
Data Index: 5125942 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.8458. Min Act: -0.1700
Data Index: 6407960 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.8145. Min Act: -0.1700
Data Index: 3093891 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.8145. Min Act: -0.1700
Data Index: 5709238 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.7833. Min Act: -0.1700
Data Index: 3024217 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.7833. Min Act: -0.1700
Data Index: 3072207 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.7520. Min Act: -0.1700
Data Index: 2564808 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.7208. Min Act: -0.1700
Data Index: 3274532 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.6895. Min Act: -0.1700
Data Index: 6691801 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.6895. Min Act: -0.1700
Data Index: 4979799 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.6895. Min Act: -0.1700
Data Index: 4036497 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.6583. Min Act: -0.1700
Data Index: 4588227 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.6270. Min Act: -0.1700
Data Index: 4590086 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.6270. Min Act: -0.1700
Data Index: 7838218 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.5958. Min Act: -0.1700
Data Index: 5478835 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.5958. Min Act: -0.1700
Data Index: 680657 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4083. Min Range: -8.4083
Max Act: 7.5958. Min Act: -0.1700
Data Index: 4674924 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19