Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1691 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1922. Min Range: -8.1922
Max Act: 8.1922. Min Act: -0.1700
Data Index: 6063815 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1922. Min Range: -8.1922
Max Act: 8.1922. Min Act: -0.1700
Data Index: 2000380 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1922. Min Range: -8.1922
Max Act: 8.0047. Min Act: -0.1700
Data Index: 2557685 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.9734. Min Act: -0.1700
Data Index: 3622025 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.9422. Min Act: -0.1700
Data Index: 5376764 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.9422. Min Act: -0.1700
Data Index: 8091658 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.9422. Min Act: -0.1700
Data Index: 2398201 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.9109. Min Act: -0.1700
Data Index: 3890719 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.9109. Min Act: -0.1700
Data Index: 5102372 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.7859. Min Act: -0.1700
Data Index: 5376765 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.7859. Min Act: -0.1700
Data Index: 6296061 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.8172. Min Act: -0.1700
Data Index: 5376766 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.8172. Min Act: -0.1700
Data Index: 6024262 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.7859. Min Act: -0.1700
Data Index: 6296060 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.7859. Min Act: -0.1700
Data Index: 1977855 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.7547. Min Act: -0.1700
Data Index: 6296058 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.7547. Min Act: -0.1700
Data Index: 3171743 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.7234. Min Act: -0.1700
Data Index: 6818993 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.7547. Min Act: -0.1700
Data Index: 4094260 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1922. Min Range: -8.1922
Max Act: 7.7234. Min Act: -0.1700
Data Index: 1052970 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19