Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 612 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1813. Min Range: -5.1813
Max Act: 5.1813. Min Act: -0.1700
Data Index: 4637633 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1813. Min Range: -5.1813
Max Act: 5.1501. Min Act: -0.1700
Data Index: 8359203 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1813. Min Range: -5.1813
Max Act: 5.0876. Min Act: -0.1700
Data Index: 5163850 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1813. Min Range: -5.1813
Max Act: 5.0876. Min Act: -0.1700
Data Index: 5927271 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1813. Min Range: -5.1813
Max Act: 5.0876. Min Act: -0.1700
Data Index: 261809 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1813. Min Range: -5.1813
Max Act: 5.0251. Min Act: -0.1700
Data Index: 4752594 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1813. Min Range: -5.1813
Max Act: 5.0251. Min Act: -0.1700
Data Index: 8561996 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1813. Min Range: -5.1813
Max Act: 5.0251. Min Act: -0.1700
Data Index: 4259878 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1813. Min Range: -5.1813
Max Act: 5.0251. Min Act: -0.1699
Data Index: 4016973 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9938. Min Act: -0.1700
Data Index: 5104565 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9938. Min Act: -0.1700
Data Index: 3612204 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9626. Min Act: -0.1700
Data Index: 4283239 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9626. Min Act: -0.1700
Data Index: 7317500 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9938. Min Act: -0.1700
Data Index: 6948810 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9313. Min Act: -0.1700
Data Index: 3319694 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9313. Min Act: -0.1700
Data Index: 3984238 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9313. Min Act: -0.1700
Data Index: 3239553 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9626. Min Act: -0.1700
Data Index: 2547373 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9626. Min Act: -0.1700
Data Index: 3933813 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1813. Min Range: -5.1813
Max Act: 4.9626. Min Act: -0.1700
Data Index: 5099245 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19