Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2862 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.9754. Min Act: -0.1700
Data Index: 1855828 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.9442. Min Act: -0.1700
Data Index: 3907837 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.7879. Min Act: -0.1700
Data Index: 6583414 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.7567. Min Act: -0.1700
Data Index: 78568 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.7567. Min Act: -0.1700
Data Index: 7467570 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.6317. Min Act: -0.1700
Data Index: 6676506 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.6317. Min Act: -0.1700
Data Index: 1110796 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.6317. Min Act: -0.1700
Data Index: 1645360 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5692. Min Act: -0.1700
Data Index: 6761899 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.6004. Min Act: -0.1700
Data Index: 4858355 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5692. Min Act: -0.1700
Data Index: 4377462 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5692. Min Act: -0.1700
Data Index: 3090433 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5692. Min Act: -0.1700
Data Index: 6693601 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.6004. Min Act: -0.1700
Data Index: 1898588 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5379. Min Act: -0.1700
Data Index: 6252596 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5379. Min Act: -0.1700
Data Index: 2813479 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5379. Min Act: -0.1700
Data Index: 4034866 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5379. Min Act: -0.1700
Data Index: 2813478 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5379. Min Act: -0.1700
Data Index: 3560388 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.5379. Min Act: -0.1700
Data Index: 1901158 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19