Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1922 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.5089. Min Act: -0.1700
Data Index: 8773759 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.4776. Min Act: -0.1700
Data Index: 5697350 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.4776. Min Act: -0.1700
Data Index: 3226973 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.3839. Min Act: -0.1700
Data Index: 5962443 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.3839. Min Act: -0.1700
Data Index: 7922098 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.3526. Min Act: -0.1700
Data Index: 941132 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.3526. Min Act: -0.1700
Data Index: 3761346 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.2901. Min Act: -0.1700
Data Index: 1652616 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.2276. Min Act: -0.1700
Data Index: 941537 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.2589. Min Act: -0.1700
Data Index: 3206640 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.2589. Min Act: -0.1700
Data Index: 6730104 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.2276. Min Act: -0.1700
Data Index: 6353242 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.2276. Min Act: -0.1700
Data Index: 9607 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1339. Min Act: -0.1700
Data Index: 8634336 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1339. Min Act: -0.1700
Data Index: 7059904 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1339. Min Act: -0.1700
Data Index: 2585786 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1339. Min Act: -0.1700
Data Index: 995885 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1339. Min Act: -0.1700
Data Index: 4848293 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1339. Min Act: -0.1700
Data Index: 2486327 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.0714. Min Act: -0.1700
Data Index: 6727437 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19