Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1354 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3806. Min Range: -7.3806
Max Act: 7.3806. Min Act: -0.1700
Data Index: 6120086 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3806. Min Range: -7.3806
Max Act: 7.2556. Min Act: -0.1700
Data Index: 3924953 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3806. Min Range: -7.3806
Max Act: 7.0368. Min Act: -0.1700
Data Index: 1912184 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.8806. Min Act: -0.1700
Data Index: 7388930 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.8493. Min Act: -0.1700
Data Index: 74823 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.8181. Min Act: -0.1700
Data Index: 5316405 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.7556. Min Act: -0.1700
Data Index: 8407520 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.7243. Min Act: -0.1700
Data Index: 2221609 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.7243. Min Act: -0.1700
Data Index: 2899910 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.6931. Min Act: -0.1700
Data Index: 736614 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.6618. Min Act: -0.1700
Data Index: 5316407 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.6618. Min Act: -0.1700
Data Index: 6166859 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.6618. Min Act: -0.1700
Data Index: 7236504 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.6306. Min Act: -0.1700
Data Index: 7760537 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.6306. Min Act: -0.1700
Data Index: 5504306 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.6306. Min Act: -0.1700
Data Index: 4900398 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.5993. Min Act: -0.1700
Data Index: 776962 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.6306. Min Act: -0.1700
Data Index: 2335675 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.5993. Min Act: -0.1700
Data Index: 6557610 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3806. Min Range: -7.3806
Max Act: 6.5681. Min Act: -0.1700
Data Index: 986930 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19