Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 696 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.3103. Min Act: -0.1700
Data Index: 67847 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.3103. Min Act: -0.1700
Data Index: 1665915 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.2478. Min Act: -0.1700
Data Index: 7273155 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.1853. Min Act: -0.1700
Data Index: 4102004 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.1853. Min Act: -0.1700
Data Index: 2303098 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.1228. Min Act: -0.1700
Data Index: 959652 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.1228. Min Act: -0.1700
Data Index: 3809849 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.1228. Min Act: -0.1700
Data Index: 3190835 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0916. Min Act: -0.1700
Data Index: 1224375 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0603. Min Act: -0.1700
Data Index: 4049555 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0603. Min Act: -0.1700
Data Index: 8376176 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0603. Min Act: -0.1700
Data Index: 8152559 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0603. Min Act: -0.1700
Data Index: 8009745 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0291. Min Act: -0.1700
Data Index: 4744836 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0603. Min Act: -0.1700
Data Index: 8009007 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0603. Min Act: -0.1700
Data Index: 6749171 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0603. Min Act: -0.1700
Data Index: 8773951 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0291. Min Act: -0.1700
Data Index: 676434 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0291. Min Act: -0.1700
Data Index: 7982966 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3103. Min Range: -5.3103
Max Act: 5.0291. Min Act: -0.1700
Data Index: 8634425 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19