Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1427 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.9041. Min Act: -0.1700
Data Index: 4871896 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.8416. Min Act: -0.1700
Data Index: 7016889 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.8416. Min Act: -0.1700
Data Index: 6701686 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 4118964 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 3119656 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 6553418 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 6043766 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 5129359 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.8416. Min Act: -0.1700
Data Index: 5039899 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 837697 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 2305233 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.8416. Min Act: -0.1700
Data Index: 7657610 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 2131390 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 7467548 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 2118401 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 6821051 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7791. Min Act: -0.1700
Data Index: 6810654 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7166. Min Act: -0.1700
Data Index: 1746938 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7166. Min Act: -0.1700
Data Index: 1182357 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9041. Min Range: -6.9041
Max Act: 6.7166. Min Act: -0.1700
Data Index: 4997908 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19