Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2512 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.8096. Min Act: -0.1700
Data Index: 606936 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.5909. Min Act: -0.1700
Data Index: 7244262 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.5909. Min Act: -0.1700
Data Index: 6133714 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.5284. Min Act: -0.1700
Data Index: 8461591 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.4659. Min Act: -0.1700
Data Index: 6901194 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.4659. Min Act: -0.1700
Data Index: 344054 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.4346. Min Act: -0.1700
Data Index: 6742670 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.4034. Min Act: -0.1700
Data Index: 854153 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.4034. Min Act: -0.1700
Data Index: 1049031 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.3721. Min Act: -0.1700
Data Index: 6612276 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.3409. Min Act: -0.1700
Data Index: 8347073 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.3096. Min Act: -0.1700
Data Index: 1086505 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.2784. Min Act: -0.1700
Data Index: 1929157 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.2784. Min Act: -0.1700
Data Index: 4518011 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.2784. Min Act: -0.1700
Data Index: 4190875 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.2784. Min Act: -0.1700
Data Index: 1925242 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.3096. Min Act: -0.1700
Data Index: 563381 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.2159. Min Act: -0.1700
Data Index: 6463175 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.2471. Min Act: -0.1700
Data Index: 2449747 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8096. Min Range: -6.8096
Max Act: 6.2784. Min Act: -0.1700
Data Index: 923568 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19