Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0271. Min Range: -5.0271
Max Act: 5.0271. Min Act: -0.1700
Data Index: 7286373 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.9646. Min Act: -0.1700
Data Index: 8605786 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.9021. Min Act: -0.1700
Data Index: 6812771 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.8708. Min Act: -0.1700
Data Index: 8605802 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.8396. Min Act: -0.1700
Data Index: 5445020 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.8396. Min Act: -0.1700
Data Index: 659781 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.8083. Min Act: -0.1700
Data Index: 1666136 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.8396. Min Act: -0.1700
Data Index: 5917938 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.7771. Min Act: -0.1700
Data Index: 5486523 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.7771. Min Act: -0.1700
Data Index: 3199074 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.7771. Min Act: -0.1700
Data Index: 1002690 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.7458. Min Act: -0.1700
Data Index: 3570630 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.7146. Min Act: -0.1700
Data Index: 3762133 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.6833. Min Act: -0.1700
Data Index: 3570617 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.7146. Min Act: -0.1700
Data Index: 5725394 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.6833. Min Act: -0.1700
Data Index: 4455301 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.6833. Min Act: -0.1700
Data Index: 3291262 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.6521. Min Act: -0.1700
Data Index: 2869256 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.6208. Min Act: -0.1700
Data Index: 5596185 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0271. Min Range: -5.0271
Max Act: 4.6521. Min Act: -0.1700
Data Index: 990757 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19