Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.2834. Min Act: -0.1700
Data Index: 1221192 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1842. Min Act: -0.1700
Data Index: 7634791 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1342. Min Act: -0.1700
Data Index: 4486049 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1342. Min Act: -0.1700
Data Index: 2142850 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1342. Min Act: -0.1699
Data Index: 2030500 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1175. Min Act: -0.1700
Data Index: 4411723 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1175. Min Act: -0.1700
Data Index: 8537965 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1008. Min Act: -0.1700
Data Index: 2363466 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1175. Min Act: -0.1700
Data Index: 826517 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1175. Min Act: -0.1700
Data Index: 6138811 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1008. Min Act: -0.1700
Data Index: 186030 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1008. Min Act: -0.1700
Data Index: 7618963 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.0840. Min Act: -0.1700
Data Index: 7273643 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1008. Min Act: -0.1700
Data Index: 988127 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1008. Min Act: -0.1700
Data Index: 6093370 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1008. Min Act: -0.1700
Data Index: 2245949 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1008. Min Act: -0.1700
Data Index: 1998403 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.0840. Min Act: -0.1700
Data Index: 5933788 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.1008. Min Act: -0.1700
Data Index: 2171869 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2834. Min Range: -2.2834
Max Act: 2.0840. Min Act: -0.1700
Data Index: 1681225 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19