Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 544 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.6118. Min Act: -0.1700
Data Index: 6259005 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.5493. Min Act: -0.1700
Data Index: 2765527 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.4868. Min Act: -0.1700
Data Index: 4482472 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.4556. Min Act: -0.1700
Data Index: 2292254 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.5181. Min Act: -0.1700
Data Index: 385258 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.3931. Min Act: -0.1700
Data Index: 1921522 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.4243. Min Act: -0.1700
Data Index: 4164503 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.4243. Min Act: -0.1700
Data Index: 687647 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.3306. Min Act: -0.1700
Data Index: 6621364 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.3306. Min Act: -0.1700
Data Index: 6688867 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.3306. Min Act: -0.1700
Data Index: 6008624 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.2681. Min Act: -0.1700
Data Index: 5391771 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.2993. Min Act: -0.1700
Data Index: 4378001 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.2681. Min Act: -0.1700
Data Index: 7342501 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.2056. Min Act: -0.1700
Data Index: 6047386 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.1743. Min Act: -0.1700
Data Index: 2265379 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.1743. Min Act: -0.1700
Data Index: 4471763 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.1431. Min Act: -0.1700
Data Index: 8743558 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.1431. Min Act: -0.1700
Data Index: 6118026 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6118. Min Range: -7.6118
Max Act: 7.1743. Min Act: -0.1700
Data Index: 5089471 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19