Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5574 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3034. Min Range: -4.3034
Max Act: 4.3034. Min Act: -0.1700
Data Index: 522790 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3034. Min Range: -4.3034
Max Act: 4.1784. Min Act: -0.1700
Data Index: 530408 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3034. Min Range: -4.3034
Max Act: 4.1472. Min Act: -0.1700
Data Index: 2964180 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.9909. Min Act: -0.1700
Data Index: 6969896 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.9283. Min Act: -0.1700
Data Index: 2963001 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.8658. Min Act: -0.1700
Data Index: 3613626 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.8345. Min Act: -0.1700
Data Index: 2242876 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.7876. Min Act: -0.1700
Data Index: 1164909 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.7720. Min Act: -0.1700
Data Index: 4253818 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.7720. Min Act: -0.1700
Data Index: 1219940 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.7251. Min Act: -0.1700
Data Index: 8056078 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.7251. Min Act: -0.1700
Data Index: 995721 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.6938. Min Act: -0.1700
Data Index: 1346132 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.6938. Min Act: -0.1700
Data Index: 5005575 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.6781. Min Act: -0.1700
Data Index: 4289491 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.6938. Min Act: -0.1700
Data Index: 5148756 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.6625. Min Act: -0.1700
Data Index: 8179740 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.6781. Min Act: -0.1700
Data Index: 7954134 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.6468. Min Act: -0.1700
Data Index: 8158728 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3034. Min Range: -4.3034
Max Act: 3.6625. Min Act: -0.1700
Data Index: 5261968 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19