Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6183 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0812. Min Range: -9.0812
Max Act: 9.0812. Min Act: -0.1700
Data Index: 5419663 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.7687. Min Act: -0.1700
Data Index: 6225349 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.7687. Min Act: -0.1700
Data Index: 2894131 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.7062. Min Act: -0.1700
Data Index: 5823008 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.7062. Min Act: -0.1700
Data Index: 1408087 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.5187. Min Act: -0.1700
Data Index: 7117747 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.4562. Min Act: -0.1700
Data Index: 2243489 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.3937. Min Act: -0.1700
Data Index: 1314453 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.4562. Min Act: -0.1700
Data Index: 546528 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.4562. Min Act: -0.1700
Data Index: 3827805 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.3937. Min Act: -0.1700
Data Index: 114567 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.4562. Min Act: -0.1700
Data Index: 1312972 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.3937. Min Act: -0.1700
Data Index: 6472138 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.3937. Min Act: -0.1700
Data Index: 6411397 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.3312. Min Act: -0.1700
Data Index: 5449136 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.3937. Min Act: -0.1700
Data Index: 6116417 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.3312. Min Act: -0.1700
Data Index: 7290191 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.3312. Min Act: -0.1700
Data Index: 3671917 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.3312. Min Act: -0.1700
Data Index: 8159141 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0812. Min Range: -9.0812
Max Act: 8.2687. Min Act: -0.1700
Data Index: 843039 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19