Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9868. Min Act: -0.1700
Data Index: 1371761 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9243. Min Act: -0.1700
Data Index: 6012065 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9243. Min Act: -0.1700
Data Index: 3149930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9243. Min Act: -0.1700
Data Index: 6062825 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9243. Min Act: -0.1700
Data Index: 293280 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9243. Min Act: -0.1700
Data Index: 8507402 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9243. Min Act: -0.1700
Data Index: 1478189 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1700
Data Index: 4272233 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1700
Data Index: 5517474 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1700
Data Index: 1950197 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1700
Data Index: 1857311 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8618. Min Act: -0.1700
Data Index: 7317847 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1700
Data Index: 6288108 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1699
Data Index: 1438302 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1700
Data Index: 1153531 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1700
Data Index: 976013 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1700
Data Index: 3937041 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8930. Min Act: -0.1700
Data Index: 278695 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8618. Min Act: -0.1700
Data Index: 4895280 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8618. Min Act: -0.1700
Data Index: 32044 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19