Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4571 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.5634. Min Act: -0.1700
Data Index: 4298901 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.5321. Min Act: -0.1700
Data Index: 5124087 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.4384. Min Act: -0.1700
Data Index: 7277154 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.4384. Min Act: -0.1700
Data Index: 5019733 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.4384. Min Act: -0.1700
Data Index: 5633033 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.4071. Min Act: -0.1700
Data Index: 5515298 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.4071. Min Act: -0.1700
Data Index: 4601173 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.4071. Min Act: -0.1700
Data Index: 8026730 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.4384. Min Act: -0.1700
Data Index: 7203403 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.3759. Min Act: -0.1700
Data Index: 7706194 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.3759. Min Act: -0.1700
Data Index: 5282552 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.3759. Min Act: -0.1700
Data Index: 8656636 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.4071. Min Act: -0.1700
Data Index: 5549255 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.3759. Min Act: -0.1700
Data Index: 3862277 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.3759. Min Act: -0.1700
Data Index: 7918903 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.3446. Min Act: -0.1700
Data Index: 6210585 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.3446. Min Act: -0.1700
Data Index: 610143 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.3134. Min Act: -0.1700
Data Index: 828362 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.2821. Min Act: -0.1700
Data Index: 6515007 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5634. Min Range: -5.5634
Max Act: 5.2821. Min Act: -0.1699
Data Index: 4389723 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19