Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.5001. Min Act: -0.1700
Data Index: 4066466 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.4064. Min Act: -0.1700
Data Index: 799828 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.3751. Min Act: -0.1700
Data Index: 3176301 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.3751. Min Act: -0.1700
Data Index: 4066467 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.2814. Min Act: -0.1700
Data Index: 957746 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.3126. Min Act: -0.1700
Data Index: 2101480 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.2501. Min Act: -0.1700
Data Index: 3411131 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.1564. Min Act: -0.1700
Data Index: 1003723 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.1876. Min Act: -0.1700
Data Index: 5126885 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.1564. Min Act: -0.1700
Data Index: 4929628 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.1564. Min Act: -0.1700
Data Index: 4480867 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0626. Min Act: -0.1700
Data Index: 6544079 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0314. Min Act: -0.1700
Data Index: 1362702 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0314. Min Act: -0.1700
Data Index: 8350012 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0001. Min Act: -0.1700
Data Index: 7791597 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0314. Min Act: -0.1700
Data Index: 140166 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0626. Min Act: -0.1700
Data Index: 6722016 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0626. Min Act: -0.1700
Data Index: 6690219 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0626. Min Act: -0.1700
Data Index: 2499026 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5001. Min Range: -6.5001
Max Act: 6.0001. Min Act: -0.1700
Data Index: 1744812 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19