Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2514 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.9330. Min Act: -0.1700
Data Index: 6262421 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.8987. Min Act: -0.1641
Data Index: 124590 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.8646. Min Act: -0.1692
Data Index: 1326043 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.8477. Min Act: -0.1700
Data Index: 2609497 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.8307. Min Act: -0.1698
Data Index: 2217950 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.8223. Min Act: -0.1700
Data Index: 2363403 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.8307. Min Act: -0.1700
Data Index: 6512368 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.8223. Min Act: -0.1696
Data Index: 801472 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.8139. Min Act: -0.1677
Data Index: 6330308 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7887. Min Act: -0.1700
Data Index: 1857086 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7971. Min Act: -0.1700
Data Index: 4640791 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7887. Min Act: -0.1700
Data Index: 4695722 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7887. Min Act: -0.1693
Data Index: 3756703 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7887. Min Act: -0.1700
Data Index: 2217951 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7720. Min Act: -0.1700
Data Index: 3660930 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7637. Min Act: -0.1658
Data Index: 1745008 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7637. Min Act: -0.1700
Data Index: 4938481 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7720. Min Act: -0.1697
Data Index: 8330077 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7637. Min Act: -0.1700
Data Index: 815216 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9330. Min Range: -0.9330
Max Act: 0.7554. Min Act: -0.1698
Data Index: 6262436 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19