Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5426 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3556. Min Range: -7.3556
Max Act: 7.3556. Min Act: -0.1700
Data Index: 5865786 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3556. Min Range: -7.3556
Max Act: 7.3243. Min Act: -0.1700
Data Index: 3429373 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3556. Min Range: -7.3556
Max Act: 7.2618. Min Act: -0.1700
Data Index: 5582620 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3556. Min Range: -7.3556
Max Act: 7.1681. Min Act: -0.1700
Data Index: 181222 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3556. Min Range: -7.3556
Max Act: 7.0743. Min Act: -0.1700
Data Index: 1734910 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3556. Min Range: -7.3556
Max Act: 7.0743. Min Act: -0.1700
Data Index: 7624051 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3556. Min Range: -7.3556
Max Act: 7.0118. Min Act: -0.1700
Data Index: 4478971 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3556. Min Range: -7.3556
Max Act: 7.0118. Min Act: -0.1700
Data Index: 7277198 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3556. Min Range: -7.3556
Max Act: 7.0118. Min Act: -0.1700
Data Index: 1238401 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.9806. Min Act: -0.1700
Data Index: 6968757 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.9806. Min Act: -0.1700
Data Index: 3613633 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.9493. Min Act: -0.1700
Data Index: 5858334 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.9181. Min Act: -0.1700
Data Index: 4778511 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.9181. Min Act: -0.1700
Data Index: 705384 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.8556. Min Act: -0.1700
Data Index: 4727574 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.8556. Min Act: -0.1700
Data Index: 3108028 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.8556. Min Act: -0.1700
Data Index: 3893549 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.8868. Min Act: -0.1700
Data Index: 8678660 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.8556. Min Act: -0.1700
Data Index: 520554 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3556. Min Range: -7.3556
Max Act: 6.8243. Min Act: -0.1700
Data Index: 732763 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19