Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1612 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7908. Min Act: -0.1700
Data Index: 4738526 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7908. Min Act: -0.1700
Data Index: 188307 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7596. Min Act: -0.1700
Data Index: 324832 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7596. Min Act: -0.1700
Data Index: 6407101 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7596. Min Act: -0.1700
Data Index: 3810906 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7596. Min Act: -0.1700
Data Index: 7001424 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7283. Min Act: -0.1700
Data Index: 7879839 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7596. Min Act: -0.1700
Data Index: 8448794 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7283. Min Act: -0.1700
Data Index: 4685243 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7283. Min Act: -0.1700
Data Index: 7774825 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7283. Min Act: -0.1700
Data Index: 5646361 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7283. Min Act: -0.1700
Data Index: 2902977 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6970. Min Act: -0.1700
Data Index: 1071351 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6970. Min Act: -0.1700
Data Index: 4926571 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6970. Min Act: -0.1700
Data Index: 5181724 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6970. Min Act: -0.1700
Data Index: 5459315 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6970. Min Act: -0.1700
Data Index: 2214726 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6970. Min Act: -0.1700
Data Index: 2362148 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6970. Min Act: -0.1700
Data Index: 6793140 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6970. Min Act: -0.1700
Data Index: 6943854 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19