Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1003. Min Range: -7.1003
Max Act: 7.1003. Min Act: -0.1700
Data Index: 5444245 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.9128. Min Act: -0.1700
Data Index: 1587660 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.7878. Min Act: -0.1700
Data Index: 29574 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.7253. Min Act: -0.1700
Data Index: 4902491 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.6628. Min Act: -0.1700
Data Index: 3782260 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.6628. Min Act: -0.1700
Data Index: 5176531 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.6003. Min Act: -0.1700
Data Index: 1035920 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.5690. Min Act: -0.1700
Data Index: 7254123 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.5690. Min Act: -0.1700
Data Index: 6472180 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.5690. Min Act: -0.1700
Data Index: 663227 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.5378. Min Act: -0.1700
Data Index: 841566 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.5378. Min Act: -0.1700
Data Index: 7162420 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.5378. Min Act: -0.1700
Data Index: 6733342 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.4753. Min Act: -0.1700
Data Index: 7352184 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.4753. Min Act: -0.1700
Data Index: 3713590 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.4440. Min Act: -0.1700
Data Index: 564068 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.4440. Min Act: -0.1700
Data Index: 5078587 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.4753. Min Act: -0.1700
Data Index: 8152633 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.4753. Min Act: -0.1700
Data Index: 7519137 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1003. Min Range: -7.1003
Max Act: 6.4440. Min Act: -0.1700
Data Index: 4302372 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19