Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6143 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.1708. Min Act: -0.1700
Data Index: 2472737 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.1396. Min Act: -0.1700
Data Index: 8716290 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.1083. Min Act: -0.1700
Data Index: 4576310 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.1083. Min Act: -0.1700
Data Index: 276897 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0771. Min Act: -0.1700
Data Index: 2232415 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0458. Min Act: -0.1700
Data Index: 5555804 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0458. Min Act: -0.1700
Data Index: 1874839 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0146. Min Act: -0.1700
Data Index: 2232286 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0146. Min Act: -0.1700
Data Index: 4329722 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0146. Min Act: -0.1700
Data Index: 6845775 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9833. Min Act: -0.1700
Data Index: 6991736 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9833. Min Act: -0.1700
Data Index: 5278114 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9833. Min Act: -0.1700
Data Index: 7486911 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9833. Min Act: -0.1700
Data Index: 4445645 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9521. Min Act: -0.1700
Data Index: 55347 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9521. Min Act: -0.1700
Data Index: 3403281 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9833. Min Act: -0.1700
Data Index: 7366630 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9521. Min Act: -0.1700
Data Index: 3202540 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9521. Min Act: -0.1700
Data Index: 2888995 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9208. Min Act: -0.1700
Data Index: 4256859 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19