Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2257 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.6591. Min Act: -0.1700
Data Index: 4062078 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.6591. Min Act: -0.1700
Data Index: 1794645 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.6591. Min Act: -0.1700
Data Index: 301809 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.5341. Min Act: -0.1700
Data Index: 7958967 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.5341. Min Act: -0.1700
Data Index: 7410870 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.5029. Min Act: -0.1700
Data Index: 7829649 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.3779. Min Act: -0.1700
Data Index: 7958977 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.3466. Min Act: -0.1700
Data Index: 1318636 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.3466. Min Act: -0.1700
Data Index: 2939097 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.3466. Min Act: -0.1700
Data Index: 3833386 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.3154. Min Act: -0.1700
Data Index: 7958986 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.2529. Min Act: -0.1700
Data Index: 5659398 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.2216. Min Act: -0.1700
Data Index: 4187092 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.1904. Min Act: -0.1700
Data Index: 4187093 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.1591. Min Act: -0.1700
Data Index: 1567751 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.1904. Min Act: -0.1700
Data Index: 7958970 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.1591. Min Act: -0.1700
Data Index: 7958979 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.1591. Min Act: -0.1700
Data Index: 5163970 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.1279. Min Act: -0.1700
Data Index: 2039888 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6591. Min Range: -6.6591
Max Act: 6.1591. Min Act: -0.1700
Data Index: 4433945 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19