Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6992. Min Act: -0.1700
Data Index: 7260871 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6680. Min Act: -0.1700
Data Index: 2661956 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6680. Min Act: -0.1700
Data Index: 3010881 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6680. Min Act: -0.1700
Data Index: 8556775 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6680. Min Act: -0.1700
Data Index: 1638774 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6367. Min Act: -0.1700
Data Index: 1223441 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6367. Min Act: -0.1700
Data Index: 7782776 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6367. Min Act: -0.1700
Data Index: 1915838 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6367. Min Act: -0.1700
Data Index: 4851978 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6367. Min Act: -0.1700
Data Index: 8788086 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6680. Min Act: -0.1700
Data Index: 8452007 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6055. Min Act: -0.1700
Data Index: 429624 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6055. Min Act: -0.1700
Data Index: 4580053 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.5742. Min Act: -0.1700
Data Index: 4414824 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6055. Min Act: -0.1700
Data Index: 4982002 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6055. Min Act: -0.1700
Data Index: 5262360 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6055. Min Act: -0.1700
Data Index: 1179381 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6055. Min Act: -0.1700
Data Index: 175740 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6055. Min Act: -0.1700
Data Index: 6427686 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6055. Min Act: -0.1700
Data Index: 6609968 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19