Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6388 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0721. Min Range: -3.0721
Max Act: 3.0721. Min Act: -0.1700
Data Index: 7347142 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0721. Min Range: -3.0721
Max Act: 3.0405. Min Act: -0.1700
Data Index: 4433573 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0721. Min Range: -3.0721
Max Act: 3.0405. Min Act: -0.1700
Data Index: 8096854 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0721. Min Range: -3.0721
Max Act: 3.0247. Min Act: -0.1700
Data Index: 1766509 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0721. Min Range: -3.0721
Max Act: 3.0089. Min Act: -0.1700
Data Index: 4807802 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9773. Min Act: -0.1700
Data Index: 8408493 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9773. Min Act: -0.1700
Data Index: 2605202 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9457. Min Act: -0.1700
Data Index: 1346643 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9457. Min Act: -0.1700
Data Index: 887733 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9457. Min Act: -0.1700
Data Index: 625998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9457. Min Act: -0.1700
Data Index: 6089289 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9457. Min Act: -0.1700
Data Index: 6398814 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9457. Min Act: -0.1700
Data Index: 4584010 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9457. Min Act: -0.1700
Data Index: 1682121 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9298. Min Act: -0.1700
Data Index: 4278590 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9298. Min Act: -0.1700
Data Index: 89258 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9298. Min Act: -0.1700
Data Index: 5615831 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9298. Min Act: -0.1700
Data Index: 7416409 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9140. Min Act: -0.1700
Data Index: 65391 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0721. Min Range: -3.0721
Max Act: 2.9140. Min Act: -0.1700
Data Index: 4357193 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19