Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3759 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.1616. Min Act: -0.1700
Data Index: 7005027 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.1616. Min Act: -0.1700
Data Index: 198790 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.1616. Min Act: -0.1700
Data Index: 7630939 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.1616. Min Act: -0.1700
Data Index: 6908275 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0678. Min Act: -0.1700
Data Index: 8653459 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.1303. Min Act: -0.1700
Data Index: 2310306 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.1303. Min Act: -0.1700
Data Index: 2181019 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0991. Min Act: -0.1700
Data Index: 5858829 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0991. Min Act: -0.1700
Data Index: 2594104 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0991. Min Act: -0.1700
Data Index: 4268471 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0678. Min Act: -0.1700
Data Index: 1017183 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0366. Min Act: -0.1700
Data Index: 6212781 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0678. Min Act: -0.1700
Data Index: 2169696 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0991. Min Act: -0.1700
Data Index: 2211096 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0678. Min Act: -0.1700
Data Index: 7729667 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0678. Min Act: -0.1700
Data Index: 1580838 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0991. Min Act: -0.1700
Data Index: 763207 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0678. Min Act: -0.1700
Data Index: 8066688 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0366. Min Act: -0.1700
Data Index: 8107804 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1616. Min Range: -5.1616
Max Act: 5.0678. Min Act: -0.1700
Data Index: 3860542 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19