Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5834 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0072. Min Range: -11.0072
Max Act: 11.0072. Min Act: -0.1700
Data Index: 1203208 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0072. Min Range: -11.0072
Max Act: 11.0072. Min Act: -0.1700
Data Index: 3425771 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.9447. Min Act: -0.1700
Data Index: 24143 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.8822. Min Act: -0.1700
Data Index: 8689172 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.7572. Min Act: -0.1700
Data Index: 5614993 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.6947. Min Act: -0.1700
Data Index: 1332522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.6322. Min Act: -0.1700
Data Index: 3283598 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.6322. Min Act: -0.1700
Data Index: 835469 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.6322. Min Act: -0.1700
Data Index: 4253493 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.6322. Min Act: -0.1700
Data Index: 1691038 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.6322. Min Act: -0.1700
Data Index: 7763070 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.5697. Min Act: -0.1700
Data Index: 1183098 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.5697. Min Act: -0.1700
Data Index: 2911950 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.5072. Min Act: -0.1700
Data Index: 2881977 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.5072. Min Act: -0.1700
Data Index: 6693860 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.5072. Min Act: -0.1700
Data Index: 3823484 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.5072. Min Act: -0.1700
Data Index: 5040892 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.5072. Min Act: -0.1700
Data Index: 1126842 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.4447. Min Act: -0.1700
Data Index: 6074647 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0072. Min Range: -11.0072
Max Act: 10.4447. Min Act: -0.1700
Data Index: 460584 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19