Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1560 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5503. Min Range: -5.5503
Max Act: 5.5503. Min Act: -0.1700
Data Index: 5083970 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5503. Min Range: -5.5503
Max Act: 5.1753. Min Act: -0.1700
Data Index: 7129477 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.9878. Min Act: -0.1700
Data Index: 3269707 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.9566. Min Act: -0.1700
Data Index: 1194426 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.9253. Min Act: -0.1700
Data Index: 3312616 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 5507390 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 3779408 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 7825083 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 1619739 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8316. Min Act: -0.1700
Data Index: 6422577 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8628. Min Act: -0.1700
Data Index: 7167580 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8316. Min Act: -0.1700
Data Index: 8749855 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8316. Min Act: -0.1700
Data Index: 1333748 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8003. Min Act: -0.1700
Data Index: 1881126 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8003. Min Act: -0.1700
Data Index: 1660272 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8003. Min Act: -0.1700
Data Index: 7837244 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.8003. Min Act: -0.1700
Data Index: 4892707 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.7691. Min Act: -0.1700
Data Index: 4963585 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.7691. Min Act: -0.1700
Data Index: 7207699 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5503. Min Range: -5.5503
Max Act: 4.7691. Min Act: -0.1700
Data Index: 769767 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19