Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4986. Min Act: -0.1700
Data Index: 5392418 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4361. Min Act: -0.1700
Data Index: 1782587 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4673. Min Act: -0.1700
Data Index: 6901796 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4673. Min Act: -0.1700
Data Index: 6795562 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4048. Min Act: -0.1700
Data Index: 2567513 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4048. Min Act: -0.1700
Data Index: 8401988 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4048. Min Act: -0.1700
Data Index: 3935499 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4048. Min Act: -0.1700
Data Index: 5514753 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4048. Min Act: -0.1700
Data Index: 1360566 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.3736. Min Act: -0.1700
Data Index: 6581863 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4048. Min Act: -0.1700
Data Index: 406033 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4048. Min Act: -0.1700
Data Index: 1862189 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.4048. Min Act: -0.1700
Data Index: 6650514 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.3736. Min Act: -0.1700
Data Index: 3810674 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.3736. Min Act: -0.1700
Data Index: 2994747 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.3736. Min Act: -0.1700
Data Index: 5130339 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.3736. Min Act: -0.1700
Data Index: 1904704 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.3736. Min Act: -0.1700
Data Index: 4522312 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.3736. Min Act: -0.1700
Data Index: 7516994 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4986. Min Range: -5.4986
Max Act: 5.3736. Min Act: -0.1700
Data Index: 5969110 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19