Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0883. Min Range: -2.0883
Max Act: 2.0883. Min Act: -0.1700
Data Index: 4391908 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0883. Min Range: -2.0883
Max Act: 2.0379. Min Act: -0.1700
Data Index: 8776816 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0883. Min Range: -2.0883
Max Act: 2.0041. Min Act: -0.1700
Data Index: 1572475 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0883. Min Range: -2.0883
Max Act: 2.0041. Min Act: -0.1700
Data Index: 8174567 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.9872. Min Act: -0.1700
Data Index: 3124103 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.9533. Min Act: -0.1700
Data Index: 8206197 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.9193. Min Act: -0.1700
Data Index: 3597830 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.9023. Min Act: -0.1700
Data Index: 1921407 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.8852. Min Act: -0.1700
Data Index: 7623695 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.8681. Min Act: -0.1700
Data Index: 5452423 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.8681. Min Act: -0.1700
Data Index: 7442783 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.8510. Min Act: -0.1700
Data Index: 7131664 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.8167. Min Act: -0.1700
Data Index: 3765041 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.8167. Min Act: -0.1700
Data Index: 8795986 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.8167. Min Act: -0.1700
Data Index: 7316833 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.7995. Min Act: -0.1700
Data Index: 6894734 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.7995. Min Act: -0.1700
Data Index: 5783931 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.7995. Min Act: -0.1700
Data Index: 6215791 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.7823. Min Act: -0.1700
Data Index: 1104969 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0883. Min Range: -2.0883
Max Act: 1.7995. Min Act: -0.1700
Data Index: 1053506 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19