Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0076. Min Range: -4.0076
Max Act: 4.0076. Min Act: -0.1700
Data Index: 7467600 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.9763. Min Act: -0.1700
Data Index: 3927476 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.9450. Min Act: -0.1700
Data Index: 4339913 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.9138. Min Act: -0.1700
Data Index: 8206985 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.9138. Min Act: -0.1700
Data Index: 4356130 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.9138. Min Act: -0.1700
Data Index: 5480028 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.9138. Min Act: -0.1700
Data Index: 684019 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8825. Min Act: -0.1700
Data Index: 3425376 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8825. Min Act: -0.1700
Data Index: 3960718 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8825. Min Act: -0.1700
Data Index: 7743627 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8825. Min Act: -0.1700
Data Index: 7276533 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8825. Min Act: -0.1700
Data Index: 5501794 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8825. Min Act: -0.1700
Data Index: 5204925 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8512. Min Act: -0.1700
Data Index: 7692238 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8512. Min Act: -0.1700
Data Index: 6064675 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8512. Min Act: -0.1700
Data Index: 2401841 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8512. Min Act: -0.1700
Data Index: 8022213 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8512. Min Act: -0.1700
Data Index: 3117190 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8512. Min Act: -0.1700
Data Index: 8079334 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0076. Min Range: -4.0076
Max Act: 3.8512. Min Act: -0.1700
Data Index: 4479608 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19