Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.9690. Min Act: -0.1700
Data Index: 2608907 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.8753. Min Act: -0.1700
Data Index: 955537 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.7815. Min Act: -0.1700
Data Index: 5197346 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.6878. Min Act: -0.1700
Data Index: 6254268 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.6565. Min Act: -0.1700
Data Index: 4715161 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.6253. Min Act: -0.1700
Data Index: 907045 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.5940. Min Act: -0.1700
Data Index: 1079589 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.5940. Min Act: -0.1700
Data Index: 5559329 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.5315. Min Act: -0.1700
Data Index: 6233672 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.5315. Min Act: -0.1700
Data Index: 8528986 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.4690. Min Act: -0.1700
Data Index: 6295870 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.5003. Min Act: -0.1700
Data Index: 661723 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.5003. Min Act: -0.1700
Data Index: 151154 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.4690. Min Act: -0.1700
Data Index: 3973182 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.4690. Min Act: -0.1700
Data Index: 7756340 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.4378. Min Act: -0.1700
Data Index: 1272422 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.4378. Min Act: -0.1700
Data Index: 1086828 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.4378. Min Act: -0.1700
Data Index: 3767137 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.4378. Min Act: -0.1700
Data Index: 5079827 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9690. Min Range: -6.9690
Max Act: 6.4378. Min Act: -0.1700
Data Index: 7386586 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19