Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.8949. Min Act: -0.1700
Data Index: 6123643 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.8012. Min Act: -0.1700
Data Index: 1928270 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.6762. Min Act: -0.1700
Data Index: 4984247 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.6762. Min Act: -0.1700
Data Index: 5592074 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.5512. Min Act: -0.1700
Data Index: 4631715 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.5199. Min Act: -0.1700
Data Index: 3726002 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.5199. Min Act: -0.1700
Data Index: 421767 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.4887. Min Act: -0.1700
Data Index: 2263764 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.4887. Min Act: -0.1700
Data Index: 7030519 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.4887. Min Act: -0.1700
Data Index: 1341943 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.4574. Min Act: -0.1700
Data Index: 7098341 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.4574. Min Act: -0.1700
Data Index: 701508 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.4262. Min Act: -0.1700
Data Index: 6774178 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.4262. Min Act: -0.1700
Data Index: 4094749 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.3949. Min Act: -0.1700
Data Index: 6297244 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.3637. Min Act: -0.1700
Data Index: 1427521 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.3637. Min Act: -0.1700
Data Index: 1470371 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.3637. Min Act: -0.1700
Data Index: 493066 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.3637. Min Act: -0.1700
Data Index: 6716315 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8949. Min Range: -6.8949
Max Act: 6.3324. Min Act: -0.1700
Data Index: 108387 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19