Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.7632. Min Act: -0.1700
Data Index: 5796175 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.6694. Min Act: -0.1700
Data Index: 6616952 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.6382. Min Act: -0.1700
Data Index: 3241006 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.6382. Min Act: -0.1700
Data Index: 668068 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5757. Min Act: -0.1700
Data Index: 7980070 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5757. Min Act: -0.1700
Data Index: 4510526 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5757. Min Act: -0.1700
Data Index: 5224905 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5757. Min Act: -0.1700
Data Index: 498429 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.6069. Min Act: -0.1700
Data Index: 6827862 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5444. Min Act: -0.1700
Data Index: 115459 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5444. Min Act: -0.1700
Data Index: 6449348 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5444. Min Act: -0.1700
Data Index: 3588565 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5132. Min Act: -0.1700
Data Index: 4282727 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5132. Min Act: -0.1700
Data Index: 6303329 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5132. Min Act: -0.1700
Data Index: 4375602 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.5132. Min Act: -0.1700
Data Index: 3816650 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.4819. Min Act: -0.1700
Data Index: 2512727 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.4819. Min Act: -0.1700
Data Index: 1458600 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.4819. Min Act: -0.1700
Data Index: 1537851 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7632. Min Range: -4.7632
Max Act: 4.4819. Min Act: -0.1700
Data Index: 3666714 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19