Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.9256. Min Act: -0.1700
Data Index: 4559028 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.8939. Min Act: -0.1700
Data Index: 203526 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.8780. Min Act: -0.1700
Data Index: 8234182 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.8780. Min Act: -0.1700
Data Index: 107155 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7985. Min Act: -0.1700
Data Index: 6146057 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7826. Min Act: -0.1700
Data Index: 1627 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7985. Min Act: -0.1700
Data Index: 8063029 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7826. Min Act: -0.1700
Data Index: 7745069 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7826. Min Act: -0.1700
Data Index: 3826962 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7507. Min Act: -0.1700
Data Index: 4710193 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7666. Min Act: -0.1700
Data Index: 3615180 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7666. Min Act: -0.1700
Data Index: 8176378 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7507. Min Act: -0.1700
Data Index: 4863242 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7347. Min Act: -0.1700
Data Index: 432930 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7347. Min Act: -0.1700
Data Index: 2692259 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7187. Min Act: -0.1700
Data Index: 495768 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7187. Min Act: -0.1700
Data Index: 4864108 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7187. Min Act: -0.1700
Data Index: 1910571 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7187. Min Act: -0.1700
Data Index: 8066475 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9256. Min Range: -2.9256
Max Act: 2.7347. Min Act: -0.1700
Data Index: 597732 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19