Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0911. Min Range: -6.0911
Max Act: 6.0911. Min Act: -0.1700
Data Index: 8200298 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.8724. Min Act: -0.1700
Data Index: 7395834 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.7786. Min Act: -0.1700
Data Index: 8704923 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.8099. Min Act: -0.1700
Data Index: 6711894 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.6849. Min Act: -0.1700
Data Index: 772225 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.6536. Min Act: -0.1700
Data Index: 5667578 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.6536. Min Act: -0.1700
Data Index: 1848678 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.6224. Min Act: -0.1700
Data Index: 2001056 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.5599. Min Act: -0.1700
Data Index: 208430 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.5286. Min Act: -0.1700
Data Index: 823938 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.5286. Min Act: -0.1700
Data Index: 2177448 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.5286. Min Act: -0.1700
Data Index: 6559501 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.5286. Min Act: -0.1700
Data Index: 3142582 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.5286. Min Act: -0.1700
Data Index: 479112 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.5286. Min Act: -0.1700
Data Index: 7265869 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.4661. Min Act: -0.1700
Data Index: 5958968 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.4661. Min Act: -0.1700
Data Index: 5214781 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.4349. Min Act: -0.1700
Data Index: 1461563 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.4349. Min Act: -0.1700
Data Index: 1460460 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0911. Min Range: -6.0911
Max Act: 5.4349. Min Act: -0.1700
Data Index: 8037158 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19