Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.8702. Min Act: -0.1700
Data Index: 3639018 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.8390. Min Act: -0.1700
Data Index: 2680677 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.8077. Min Act: -0.1700
Data Index: 6256496 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.7765. Min Act: -0.1700
Data Index: 1521403 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.7765. Min Act: -0.1700
Data Index: 6178323 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.7452. Min Act: -0.1700
Data Index: 6305753 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.7452. Min Act: -0.1700
Data Index: 1054891 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.6827. Min Act: -0.1700
Data Index: 1614984 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.6827. Min Act: -0.1700
Data Index: 921292 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.6515. Min Act: -0.1700
Data Index: 7931835 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.6515. Min Act: -0.1700
Data Index: 1712634 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.6515. Min Act: -0.1700
Data Index: 2652564 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.6515. Min Act: -0.1700
Data Index: 2448285 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.6202. Min Act: -0.1700
Data Index: 3828600 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.5890. Min Act: -0.1700
Data Index: 312046 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.6202. Min Act: -0.1700
Data Index: 5981171 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.5890. Min Act: -0.1700
Data Index: 1440637 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.5577. Min Act: -0.1700
Data Index: 2432321 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.5577. Min Act: -0.1700
Data Index: 2906265 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8702. Min Range: -4.8702
Max Act: 4.5265. Min Act: -0.1700
Data Index: 7955777 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19