Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4713 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0701. Min Range: -2.0701
Max Act: 2.0701. Min Act: -0.1700
Data Index: 1312863 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0701. Min Range: -2.0701
Max Act: 2.0364. Min Act: -0.1700
Data Index: 1411903 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0701. Min Range: -2.0701
Max Act: 2.0364. Min Act: -0.1700
Data Index: 2508479 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0701. Min Range: -2.0701
Max Act: 2.0027. Min Act: -0.1700
Data Index: 308863 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9773. Min Act: -0.1700
Data Index: 2127631 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9773. Min Act: -0.1700
Data Index: 4707323 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9604. Min Act: -0.1700
Data Index: 6297757 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9604. Min Act: -0.1700
Data Index: 3156203 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9519. Min Act: -0.1700
Data Index: 7576177 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9519. Min Act: -0.1700
Data Index: 3783755 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9349. Min Act: -0.1700
Data Index: 5884705 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9434. Min Act: -0.1699
Data Index: 4914399 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9349. Min Act: -0.1700
Data Index: 90861 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9264. Min Act: -0.1700
Data Index: 2907427 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9179. Min Act: -0.1696
Data Index: 8323614 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9179. Min Act: -0.1700
Data Index: 4882846 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9094. Min Act: -0.1700
Data Index: 1423643 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9009. Min Act: -0.1700
Data Index: 3480477 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.9009. Min Act: -0.1700
Data Index: 5021777 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0701. Min Range: -2.0701
Max Act: 1.8923. Min Act: -0.1700
Data Index: 6112763 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19