Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.5882. Min Act: -0.1700
Data Index: 6926680 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.5726. Min Act: -0.1700
Data Index: 7702084 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.5726. Min Act: -0.1700
Data Index: 3202277 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.5413. Min Act: -0.1700
Data Index: 1598521 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.5256. Min Act: -0.1700
Data Index: 7894481 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.5256. Min Act: -0.1700
Data Index: 3858590 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4629. Min Act: -0.1700
Data Index: 8089960 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4943. Min Act: -0.1700
Data Index: 1716960 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4786. Min Act: -0.1700
Data Index: 5685002 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4629. Min Act: -0.1700
Data Index: 6112678 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4786. Min Act: -0.1700
Data Index: 3741326 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4786. Min Act: -0.1700
Data Index: 6513824 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4473. Min Act: -0.1700
Data Index: 541227 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4473. Min Act: -0.1700
Data Index: 8607869 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4316. Min Act: -0.1700
Data Index: 6601529 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4473. Min Act: -0.1700
Data Index: 5190085 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4316. Min Act: -0.1700
Data Index: 2325293 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4316. Min Act: -0.1700
Data Index: 8638465 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4159. Min Act: -0.1700
Data Index: 8176360 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5882. Min Range: -3.5882
Max Act: 3.4159. Min Act: -0.1700
Data Index: 737624 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19