Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4490 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.9083. Min Act: -0.1700
Data Index: 4151877 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.8770. Min Act: -0.1700
Data Index: 1039470 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.7208. Min Act: -0.1700
Data Index: 3416660 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.7208. Min Act: -0.1700
Data Index: 1490714 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.7520. Min Act: -0.1700
Data Index: 259078 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.6895. Min Act: -0.1700
Data Index: 8813677 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.6895. Min Act: -0.1700
Data Index: 4217798 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.6895. Min Act: -0.1700
Data Index: 7005987 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.6583. Min Act: -0.1700
Data Index: 8407942 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.6270. Min Act: -0.1700
Data Index: 1524344 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.6270. Min Act: -0.1700
Data Index: 6117581 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.5958. Min Act: -0.1700
Data Index: 2832854 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.5958. Min Act: -0.1700
Data Index: 8578193 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.5333. Min Act: -0.1700
Data Index: 2831298 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.5645. Min Act: -0.1700
Data Index: 2471002 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.5645. Min Act: -0.1700
Data Index: 4526774 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.5645. Min Act: -0.1700
Data Index: 6104476 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.5333. Min Act: -0.1700
Data Index: 5573102 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.5333. Min Act: -0.1700
Data Index: 4357404 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9083. Min Range: -5.9083
Max Act: 5.5333. Min Act: -0.1700
Data Index: 3903757 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19