Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 383 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.9829. Min Act: -0.1700
Data Index: 320883 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.9829. Min Act: -0.1700
Data Index: 7453049 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.9204. Min Act: -0.1700
Data Index: 7767856 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.9204. Min Act: -0.1700
Data Index: 1660486 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.9204. Min Act: -0.1700
Data Index: 5191521 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.9204. Min Act: -0.1700
Data Index: 4272801 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.8579. Min Act: -0.1700
Data Index: 7588578 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.8579. Min Act: -0.1700
Data Index: 8391432 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7954. Min Act: -0.1700
Data Index: 4288455 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7954. Min Act: -0.1700
Data Index: 6154712 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7954. Min Act: -0.1700
Data Index: 7384703 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7954. Min Act: -0.1700
Data Index: 4400538 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7954. Min Act: -0.1700
Data Index: 1665344 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7954. Min Act: -0.1700
Data Index: 1489244 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7329. Min Act: -0.1700
Data Index: 2011555 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.6704. Min Act: -0.1700
Data Index: 2428691 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7329. Min Act: -0.1700
Data Index: 5594080 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7329. Min Act: -0.1700
Data Index: 861394 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7329. Min Act: -0.1700
Data Index: 3371673 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9829. Min Range: -9.9829
Max Act: 9.7329. Min Act: -0.1700
Data Index: 4541231 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19