Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5246 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3821. Min Range: -10.3821
Max Act: 10.3821. Min Act: -0.1700
Data Index: 5497208 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3821. Min Range: -10.3821
Max Act: 10.2571. Min Act: -0.1700
Data Index: 3115858 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3821. Min Range: -10.3821
Max Act: 10.0696. Min Act: -0.1700
Data Index: 1178121 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3821. Min Range: -10.3821
Max Act: 10.0071. Min Act: -0.1700
Data Index: 8463966 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.8821. Min Act: -0.1700
Data Index: 2451826 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.8821. Min Act: -0.1700
Data Index: 6206691 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.8196. Min Act: -0.1700
Data Index: 3970973 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.8196. Min Act: -0.1700
Data Index: 7173138 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.8196. Min Act: -0.1700
Data Index: 6070157 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.8196. Min Act: -0.1700
Data Index: 1379286 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.7571. Min Act: -0.1700
Data Index: 425170 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.7571. Min Act: -0.1700
Data Index: 7286496 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.7571. Min Act: -0.1700
Data Index: 8224933 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.6946. Min Act: -0.1700
Data Index: 2631072 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.6946. Min Act: -0.1700
Data Index: 7773962 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.6946. Min Act: -0.1700
Data Index: 7812709 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.6321. Min Act: -0.1700
Data Index: 8225456 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.6321. Min Act: -0.1700
Data Index: 1469083 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.6321. Min Act: -0.1700
Data Index: 3653565 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3821. Min Range: -10.3821
Max Act: 9.6946. Min Act: -0.1700
Data Index: 730691 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19