Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.9242. Min Act: -0.1700
Data Index: 1771360 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.9242. Min Act: -0.1700
Data Index: 5897501 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.7992. Min Act: -0.1700
Data Index: 1544255 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.7055. Min Act: -0.1700
Data Index: 5362125 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.7055. Min Act: -0.1700
Data Index: 8629841 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.7055. Min Act: -0.1700
Data Index: 1504652 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6742. Min Act: -0.1700
Data Index: 953605 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6742. Min Act: -0.1700
Data Index: 1786674 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6742. Min Act: -0.1700
Data Index: 3224317 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6430. Min Act: -0.1700
Data Index: 351447 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6430. Min Act: -0.1700
Data Index: 6553251 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6117. Min Act: -0.1700
Data Index: 7072943 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6117. Min Act: -0.1700
Data Index: 5953497 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6117. Min Act: -0.1700
Data Index: 994289 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.5492. Min Act: -0.1700
Data Index: 8830344 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.5492. Min Act: -0.1700
Data Index: 5654929 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.5805. Min Act: -0.1700
Data Index: 8811663 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.5492. Min Act: -0.1700
Data Index: 3653218 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.5492. Min Act: -0.1700
Data Index: 8035571 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.5492. Min Act: -0.1700
Data Index: 2119357 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19