Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 326 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.9644. Min Act: -0.1700
Data Index: 3735216 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.7455. Min Act: -0.1700
Data Index: 6413841 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.7299. Min Act: -0.1700
Data Index: 8027786 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6986. Min Act: -0.1700
Data Index: 2554293 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6830. Min Act: -0.1700
Data Index: 4074398 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6673. Min Act: -0.1700
Data Index: 4566472 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6673. Min Act: -0.1700
Data Index: 4966251 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6673. Min Act: -0.1700
Data Index: 6334209 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6673. Min Act: -0.1700
Data Index: 1126906 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6360. Min Act: -0.1700
Data Index: 5659421 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6360. Min Act: -0.1700
Data Index: 590973 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6360. Min Act: -0.1700
Data Index: 7512316 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6204. Min Act: -0.1700
Data Index: 615059 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6204. Min Act: -0.1700
Data Index: 1365767 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6204. Min Act: -0.1700
Data Index: 2075151 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.5891. Min Act: -0.1700
Data Index: 1499745 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.6047. Min Act: -0.1700
Data Index: 4201032 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.5891. Min Act: -0.1700
Data Index: 5999341 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.5734. Min Act: -0.1700
Data Index: 5165077 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9644. Min Range: -3.9644
Max Act: 3.5734. Min Act: -0.1700
Data Index: 1457515 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19