Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2831. Min Range: -9.2831
Max Act: 9.2831. Min Act: -0.1700
Data Index: 6361579 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2831. Min Range: -9.2831
Max Act: 9.1581. Min Act: -0.1700
Data Index: 12897 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2831. Min Range: -9.2831
Max Act: 9.0956. Min Act: -0.1700
Data Index: 4904653 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2831. Min Range: -9.2831
Max Act: 9.0331. Min Act: -0.1700
Data Index: 7480488 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.9081. Min Act: -0.1700
Data Index: 5350968 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.7831. Min Act: -0.1700
Data Index: 2505802 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.7206. Min Act: -0.1700
Data Index: 4236601 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.7206. Min Act: -0.1700
Data Index: 240837 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.7206. Min Act: -0.1700
Data Index: 7351488 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.7206. Min Act: -0.1700
Data Index: 5285726 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.6581. Min Act: -0.1700
Data Index: 1130430 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.5956. Min Act: -0.1700
Data Index: 5425751 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.5956. Min Act: -0.1700
Data Index: 4622923 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.5956. Min Act: -0.1700
Data Index: 4497384 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.5956. Min Act: -0.1700
Data Index: 606885 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.5331. Min Act: -0.1700
Data Index: 7322611 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.5331. Min Act: -0.1700
Data Index: 997258 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.5331. Min Act: -0.1700
Data Index: 1939084 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.5331. Min Act: -0.1700
Data Index: 918615 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2831. Min Range: -9.2831
Max Act: 8.5331. Min Act: -0.1700
Data Index: 7790381 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19