Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4771. Min Range: -6.4771
Max Act: 6.4771. Min Act: -0.1700
Data Index: 314125 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4771. Min Range: -6.4771
Max Act: 6.3521. Min Act: -0.1700
Data Index: 195605 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4771. Min Range: -6.4771
Max Act: 6.1333. Min Act: -0.1700
Data Index: 6567902 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4771. Min Range: -6.4771
Max Act: 6.0708. Min Act: -0.1700
Data Index: 6863579 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4771. Min Range: -6.4771
Max Act: 6.0708. Min Act: -0.1700
Data Index: 7071571 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4771. Min Range: -6.4771
Max Act: 6.0083. Min Act: -0.1700
Data Index: 6530102 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4771. Min Range: -6.4771
Max Act: 6.0396. Min Act: -0.1700
Data Index: 3024630 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4771. Min Range: -6.4771
Max Act: 6.0083. Min Act: -0.1700
Data Index: 432719 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4771. Min Range: -6.4771
Max Act: 6.0083. Min Act: -0.1700
Data Index: 1017261 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.9771. Min Act: -0.1700
Data Index: 4265605 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.9771. Min Act: -0.1700
Data Index: 2567224 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.9458. Min Act: -0.1700
Data Index: 3610201 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.9146. Min Act: -0.1700
Data Index: 2076627 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.9146. Min Act: -0.1700
Data Index: 3646501 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.9146. Min Act: -0.1700
Data Index: 7660737 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.9146. Min Act: -0.1700
Data Index: 4464149 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.9146. Min Act: -0.1700
Data Index: 6567899 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.8833. Min Act: -0.1700
Data Index: 2446586 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.9146. Min Act: -0.1700
Data Index: 15237 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4771. Min Range: -6.4771
Max Act: 5.8833. Min Act: -0.1700
Data Index: 1256767 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19