Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5195 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.9860. Min Act: -0.1700
Data Index: 7046775 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.7360. Min Act: -0.1700
Data Index: 5399168 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.6110. Min Act: -0.1700
Data Index: 5027438 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.6735. Min Act: -0.1700
Data Index: 2766156 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.6735. Min Act: -0.1700
Data Index: 8760612 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.6110. Min Act: -0.1700
Data Index: 7118352 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.6110. Min Act: -0.1700
Data Index: 583183 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.6110. Min Act: -0.1700
Data Index: 6521841 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.5485. Min Act: -0.1700
Data Index: 6364016 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.4860. Min Act: -0.1700
Data Index: 2958417 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.4860. Min Act: -0.1700
Data Index: 8766938 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.4860. Min Act: -0.1700
Data Index: 8788627 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.4860. Min Act: -0.1700
Data Index: 1004105 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.4235. Min Act: -0.1700
Data Index: 1856060 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.4235. Min Act: -0.1700
Data Index: 408836 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.3610. Min Act: -0.1700
Data Index: 5863820 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.3610. Min Act: -0.1700
Data Index: 6973544 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.3610. Min Act: -0.1700
Data Index: 3965745 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.2360. Min Act: -0.1700
Data Index: 6628976 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9860. Min Range: -9.9860
Max Act: 9.2985. Min Act: -0.1700
Data Index: 520713 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19