Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.6844. Min Act: -0.1700
Data Index: 7502159 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.6531. Min Act: -0.1700
Data Index: 7502158 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.5592. Min Act: -0.1700
Data Index: 5200374 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.5592. Min Act: -0.1700
Data Index: 7405025 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.5279. Min Act: -0.1700
Data Index: 2170564 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.5279. Min Act: -0.1700
Data Index: 4640735 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.5279. Min Act: -0.1700
Data Index: 4287778 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4965. Min Act: -0.1700
Data Index: 7751992 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4965. Min Act: -0.1700
Data Index: 7723331 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4965. Min Act: -0.1700
Data Index: 7514870 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4965. Min Act: -0.1700
Data Index: 4309206 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4965. Min Act: -0.1700
Data Index: 3366957 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4965. Min Act: -0.1700
Data Index: 8219697 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4652. Min Act: -0.1700
Data Index: 1154710 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4965. Min Act: -0.1700
Data Index: 2326987 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4652. Min Act: -0.1700
Data Index: 7372735 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4652. Min Act: -0.1700
Data Index: 953195 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4652. Min Act: -0.1700
Data Index: 6886400 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4652. Min Act: -0.1700
Data Index: 5860954 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6844. Min Range: -3.6844
Max Act: 3.4652. Min Act: -0.1700
Data Index: 742791 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19