Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0040. Min Range: -9.0040
Max Act: 9.0040. Min Act: -0.1700
Data Index: 7835533 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.6915. Min Act: -0.1700
Data Index: 8576421 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.5040. Min Act: -0.1700
Data Index: 1592280 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.4415. Min Act: -0.1700
Data Index: 6454359 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.4415. Min Act: -0.1700
Data Index: 6008079 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.3790. Min Act: -0.1700
Data Index: 7465082 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.3790. Min Act: -0.1700
Data Index: 3343098 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.3165. Min Act: -0.1700
Data Index: 6720973 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.3790. Min Act: -0.1700
Data Index: 2543082 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.3165. Min Act: -0.1700
Data Index: 757690 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.3790. Min Act: -0.1700
Data Index: 7814300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.3165. Min Act: -0.1700
Data Index: 4762443 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.2540. Min Act: -0.1700
Data Index: 6954477 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.2540. Min Act: -0.1700
Data Index: 607104 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.2540. Min Act: -0.1700
Data Index: 7777445 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.2228. Min Act: -0.1700
Data Index: 883181 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.2228. Min Act: -0.1700
Data Index: 6322744 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.2228. Min Act: -0.1700
Data Index: 6127070 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.2228. Min Act: -0.1700
Data Index: 6063645 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0040. Min Range: -9.0040
Max Act: 8.1915. Min Act: -0.1700
Data Index: 737944 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19