Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3337 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3034. Min Range: -9.3034
Max Act: 9.3034. Min Act: -0.1700
Data Index: 5531426 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3034. Min Range: -9.3034
Max Act: 9.3034. Min Act: -0.1700
Data Index: 622064 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3034. Min Range: -9.3034
Max Act: 9.2409. Min Act: -0.1700
Data Index: 4250652 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3034. Min Range: -9.3034
Max Act: 9.1784. Min Act: -0.1700
Data Index: 1761592 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3034. Min Range: -9.3034
Max Act: 9.1784. Min Act: -0.1700
Data Index: 7896985 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.8659. Min Act: -0.1700
Data Index: 7869488 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.8659. Min Act: -0.1700
Data Index: 5497196 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.8034. Min Act: -0.1700
Data Index: 5883507 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.7409. Min Act: -0.1700
Data Index: 8617924 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.7409. Min Act: -0.1700
Data Index: 2571287 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.7409. Min Act: -0.1700
Data Index: 5798730 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.6784. Min Act: -0.1700
Data Index: 4816061 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.6159. Min Act: -0.1700
Data Index: 5015523 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.6159. Min Act: -0.1700
Data Index: 6487907 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.6784. Min Act: -0.1700
Data Index: 6547948 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.5534. Min Act: -0.1700
Data Index: 3615623 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.4909. Min Act: -0.1700
Data Index: 5326266 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.4909. Min Act: -0.1700
Data Index: 8492055 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.4909. Min Act: -0.1700
Data Index: 3861051 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3034. Min Range: -9.3034
Max Act: 8.4284. Min Act: -0.1700
Data Index: 3731745 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19