Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4400 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.8232. Min Act: -0.1700
Data Index: 7456584 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.7295. Min Act: -0.1700
Data Index: 5043610 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.6982. Min Act: -0.1700
Data Index: 4863310 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.6357. Min Act: -0.1700
Data Index: 6108017 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 2780683 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.5732. Min Act: -0.1700
Data Index: 3325006 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.5732. Min Act: -0.1700
Data Index: 4854815 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4795. Min Act: -0.1700
Data Index: 3909992 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.5107. Min Act: -0.1700
Data Index: 968977 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4795. Min Act: -0.1700
Data Index: 2449301 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4795. Min Act: -0.1700
Data Index: 4135212 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4795. Min Act: -0.1700
Data Index: 137011 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4482. Min Act: -0.1700
Data Index: 4847637 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4482. Min Act: -0.1700
Data Index: 1299505 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4482. Min Act: -0.1700
Data Index: 1378809 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4482. Min Act: -0.1700
Data Index: 8744524 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4170. Min Act: -0.1700
Data Index: 426559 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4482. Min Act: -0.1700
Data Index: 653236 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4170. Min Act: -0.1700
Data Index: 3565869 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8232. Min Range: -5.8232
Max Act: 5.4170. Min Act: -0.1700
Data Index: 2063101 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19