Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0143. Min Range: -5.0143
Max Act: 5.0143. Min Act: -0.1700
Data Index: 2280328 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.8893. Min Act: -0.1700
Data Index: 4675899 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.8268. Min Act: -0.1700
Data Index: 5010016 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.8268. Min Act: -0.1700
Data Index: 6590814 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.7643. Min Act: -0.1700
Data Index: 3484077 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.7018. Min Act: -0.1700
Data Index: 3802403 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.6706. Min Act: -0.1700
Data Index: 5743453 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.6081. Min Act: -0.1700
Data Index: 8335841 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.6081. Min Act: -0.1700
Data Index: 1715703 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5768. Min Act: -0.1700
Data Index: 8719681 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.6081. Min Act: -0.1700
Data Index: 7826236 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5768. Min Act: -0.1700
Data Index: 1712237 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5768. Min Act: -0.1700
Data Index: 7082206 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5456. Min Act: -0.1700
Data Index: 4448092 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5456. Min Act: -0.1700
Data Index: 3121199 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5456. Min Act: -0.1700
Data Index: 8316256 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5143. Min Act: -0.1700
Data Index: 1398297 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5143. Min Act: -0.1700
Data Index: 2895815 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5143. Min Act: -0.1700
Data Index: 4357745 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0143. Min Range: -5.0143
Max Act: 4.5143. Min Act: -0.1700
Data Index: 6454722 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19