Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.5769. Min Act: -0.1700
Data Index: 7446777 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.3582. Min Act: -0.1700
Data Index: 7541989 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.3582. Min Act: -0.1700
Data Index: 8122473 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.3269. Min Act: -0.1700
Data Index: 5552246 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.2332. Min Act: -0.1700
Data Index: 8220104 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.2019. Min Act: -0.1700
Data Index: 4577714 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.1707. Min Act: -0.1700
Data Index: 5271180 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.1707. Min Act: -0.1700
Data Index: 8593180 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.1394. Min Act: -0.1700
Data Index: 7950090 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.1707. Min Act: -0.1700
Data Index: 5848809 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.1082. Min Act: -0.1700
Data Index: 846323 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5769. Min Range: -6.5769
Max Act: 5.9832. Min Act: -0.1700
Data Index: 997994 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.0144. Min Act: -0.1700
Data Index: 3325937 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5769. Min Range: -6.5769
Max Act: 6.0144. Min Act: -0.1700
Data Index: 1972327 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5769. Min Range: -6.5769
Max Act: 5.9832. Min Act: -0.1700
Data Index: 2648744 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5769. Min Range: -6.5769
Max Act: 5.9832. Min Act: -0.1700
Data Index: 6388066 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5769. Min Range: -6.5769
Max Act: 5.9519. Min Act: -0.1700
Data Index: 1730539 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5769. Min Range: -6.5769
Max Act: 5.8894. Min Act: -0.1700
Data Index: 3259107 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5769. Min Range: -6.5769
Max Act: 5.8894. Min Act: -0.1700
Data Index: 263622 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5769. Min Range: -6.5769
Max Act: 5.8894. Min Act: -0.1700
Data Index: 5902102 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19