Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 211 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.9233. Min Act: -0.1700
Data Index: 704011 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.8720. Min Act: -0.1651
Data Index: 2412494 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.7378. Min Act: -0.1700
Data Index: 2371374 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.7295. Min Act: -0.1700
Data Index: 993758 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.7213. Min Act: -0.1699
Data Index: 5632171 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.7295. Min Act: -0.1700
Data Index: 5544946 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.7213. Min Act: -0.1604
Data Index: 6766845 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6886. Min Act: -0.1676
Data Index: 7155992 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6886. Min Act: -0.1440
Data Index: 1403742 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6805. Min Act: -0.1700
Data Index: 7625138 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6886. Min Act: -0.1521
Data Index: 7403300 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6805. Min Act: -0.1678
Data Index: 4793787 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6643. Min Act: -0.1698
Data Index: 39967 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6724. Min Act: -0.1700
Data Index: 2256493 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6643. Min Act: -0.1290
Data Index: 4036255 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6482. Min Act: -0.1699
Data Index: 2355251 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6482. Min Act: -0.1699
Data Index: 6374605 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6482. Min Act: -0.1698
Data Index: 8687613 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6482. Min Act: -0.1641
Data Index: 6689533 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9233. Min Range: -0.9233
Max Act: 0.6322. Min Act: -0.1679
Data Index: 2120967 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19