Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.6430. Min Act: -0.1700
Data Index: 1460465 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.4555. Min Act: -0.1700
Data Index: 5019764 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.4243. Min Act: -0.1700
Data Index: 5592145 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.4243. Min Act: -0.1700
Data Index: 5038039 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.3618. Min Act: -0.1700
Data Index: 6697798 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.3305. Min Act: -0.1700
Data Index: 5019774 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.3305. Min Act: -0.1700
Data Index: 455616 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.3305. Min Act: -0.1700
Data Index: 108915 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.2680. Min Act: -0.1700
Data Index: 7147889 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.2680. Min Act: -0.1700
Data Index: 3012192 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.2680. Min Act: -0.1700
Data Index: 8167361 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.2680. Min Act: -0.1700
Data Index: 7198317 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.2055. Min Act: -0.1700
Data Index: 5998768 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.2055. Min Act: -0.1700
Data Index: 6325721 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.1743. Min Act: -0.1700
Data Index: 8406433 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.1430. Min Act: -0.1700
Data Index: 4005505 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.1430. Min Act: -0.1700
Data Index: 4348170 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.1743. Min Act: -0.1700
Data Index: 4104619 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.1430. Min Act: -0.1700
Data Index: 5862469 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6430. Min Range: -6.6430
Max Act: 6.1430. Min Act: -0.1700
Data Index: 3834470 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19