Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.8097. Min Act: -0.1700
Data Index: 1729672 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.7159. Min Act: -0.1700
Data Index: 3813568 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.7003. Min Act: -0.1700
Data Index: 5049924 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.7003. Min Act: -0.1700
Data Index: 8246301 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.7003. Min Act: -0.1700
Data Index: 6869791 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6690. Min Act: -0.1700
Data Index: 4252495 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6846. Min Act: -0.1700
Data Index: 5812481 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6690. Min Act: -0.1700
Data Index: 3359913 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6533. Min Act: -0.1700
Data Index: 4549474 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6533. Min Act: -0.1700
Data Index: 6480523 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6377. Min Act: -0.1700
Data Index: 1930629 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6533. Min Act: -0.1700
Data Index: 3728808 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6220. Min Act: -0.1700
Data Index: 1054849 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6220. Min Act: -0.1700
Data Index: 7349569 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6064. Min Act: -0.1700
Data Index: 8140523 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6064. Min Act: -0.1700
Data Index: 4674352 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.6064. Min Act: -0.1700
Data Index: 5427757 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.5907. Min Act: -0.1700
Data Index: 7689908 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.5907. Min Act: -0.1700
Data Index: 7415882 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8097. Min Range: -3.8097
Max Act: 3.5907. Min Act: -0.1700
Data Index: 6089764 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19