Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 521 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2059. Min Range: -8.2059
Max Act: 8.2059. Min Act: -0.1700
Data Index: 3659828 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2059. Min Range: -8.2059
Max Act: 8.0184. Min Act: -0.1700
Data Index: 6271589 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2059. Min Range: -8.2059
Max Act: 8.0809. Min Act: -0.1700
Data Index: 5744706 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2059. Min Range: -8.2059
Max Act: 8.0184. Min Act: -0.1700
Data Index: 4431545 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.9559. Min Act: -0.1700
Data Index: 2189202 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8934. Min Act: -0.1700
Data Index: 8340545 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8934. Min Act: -0.1700
Data Index: 3792308 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8934. Min Act: -0.1700
Data Index: 3741487 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8309. Min Act: -0.1700
Data Index: 5601175 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8309. Min Act: -0.1700
Data Index: 5097868 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8309. Min Act: -0.1700
Data Index: 2384750 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.7684. Min Act: -0.1700
Data Index: 2063631 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8309. Min Act: -0.1700
Data Index: 7163744 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8309. Min Act: -0.1700
Data Index: 3758359 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.7684. Min Act: -0.1700
Data Index: 2224114 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8309. Min Act: -0.1700
Data Index: 1310892 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.7684. Min Act: -0.1700
Data Index: 7516691 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.8309. Min Act: -0.1700
Data Index: 7004178 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.7059. Min Act: -0.1700
Data Index: 7329740 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2059. Min Range: -8.2059
Max Act: 7.7059. Min Act: -0.1700
Data Index: 3621820 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19