Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4753. Min Range: -8.4753
Max Act: 8.4753. Min Act: -0.1700
Data Index: 303329 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4753. Min Range: -8.4753
Max Act: 8.0378. Min Act: -0.1700
Data Index: 3996915 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.8503. Min Act: -0.1700
Data Index: 7989688 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.7878. Min Act: -0.1700
Data Index: 4219080 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.7878. Min Act: -0.1700
Data Index: 7690938 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.7253. Min Act: -0.1700
Data Index: 2852081 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.7253. Min Act: -0.1700
Data Index: 2328215 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.7253. Min Act: -0.1700
Data Index: 3520862 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.7253. Min Act: -0.1700
Data Index: 5505024 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.7253. Min Act: -0.1700
Data Index: 7668149 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.6003. Min Act: -0.1700
Data Index: 8235809 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.6628. Min Act: -0.1700
Data Index: 4125609 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.6003. Min Act: -0.1700
Data Index: 2559802 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.4128. Min Act: -0.1700
Data Index: 2657943 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.4753. Min Act: -0.1700
Data Index: 1861729 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.4128. Min Act: -0.1700
Data Index: 1979510 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.3815. Min Act: -0.1700
Data Index: 8103652 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.3815. Min Act: -0.1700
Data Index: 7039260 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.3503. Min Act: -0.1700
Data Index: 8553749 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4753. Min Range: -8.4753
Max Act: 7.3503. Min Act: -0.1700
Data Index: 2935465 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19