Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4344 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.4762. Min Act: -0.1700
Data Index: 8491516 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.4762. Min Act: -0.1700
Data Index: 7204953 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.3512. Min Act: -0.1700
Data Index: 1308640 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.2262. Min Act: -0.1700
Data Index: 97616 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.2262. Min Act: -0.1700
Data Index: 7855450 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.1637. Min Act: -0.1700
Data Index: 3005115 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.1012. Min Act: -0.1700
Data Index: 5606234 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.1012. Min Act: -0.1700
Data Index: 555720 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.1012. Min Act: -0.1700
Data Index: 4705719 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.1012. Min Act: -0.1700
Data Index: 8776180 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.0387. Min Act: -0.1700
Data Index: 5007405 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4762. Min Range: -10.4762
Max Act: 10.1012. Min Act: -0.1700
Data Index: 181199 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4762. Min Range: -10.4762
Max Act: 9.9762. Min Act: -0.1700
Data Index: 5362924 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4762. Min Range: -10.4762
Max Act: 9.9762. Min Act: -0.1700
Data Index: 828087 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4762. Min Range: -10.4762
Max Act: 9.9762. Min Act: -0.1699
Data Index: 242889 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4762. Min Range: -10.4762
Max Act: 9.9137. Min Act: -0.1700
Data Index: 6835670 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4762. Min Range: -10.4762
Max Act: 9.8512. Min Act: -0.1700
Data Index: 3032396 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4762. Min Range: -10.4762
Max Act: 9.9137. Min Act: -0.1700
Data Index: 5269907 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4762. Min Range: -10.4762
Max Act: 9.9137. Min Act: -0.1700
Data Index: 4496490 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4762. Min Range: -10.4762
Max Act: 9.9137. Min Act: -0.1700
Data Index: 816821 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19