Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0228. Min Range: -6.0228
Max Act: 6.0228. Min Act: -0.1700
Data Index: 840363 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.9291. Min Act: -0.1700
Data Index: 8695120 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.7728. Min Act: -0.1700
Data Index: 8005754 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.7103. Min Act: -0.1700
Data Index: 5237191 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.7103. Min Act: -0.1700
Data Index: 3725362 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.6478. Min Act: -0.1700
Data Index: 8265806 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.6478. Min Act: -0.1700
Data Index: 24831 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.6478. Min Act: -0.1700
Data Index: 3051600 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.6791. Min Act: -0.1700
Data Index: 4791619 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.6478. Min Act: -0.1700
Data Index: 5442664 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.5853. Min Act: -0.1700
Data Index: 6615152 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.6166. Min Act: -0.1700
Data Index: 7802484 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.5853. Min Act: -0.1700
Data Index: 247903 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.5853. Min Act: -0.1700
Data Index: 3500214 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.6166. Min Act: -0.1700
Data Index: 6565749 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.5541. Min Act: -0.1700
Data Index: 4870064 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.5541. Min Act: -0.1700
Data Index: 3335464 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.5541. Min Act: -0.1700
Data Index: 8484549 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.5228. Min Act: -0.1700
Data Index: 3132035 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0228. Min Range: -6.0228
Max Act: 5.5228. Min Act: -0.1700
Data Index: 7853293 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19