Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2578 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4551. Min Range: -8.4551
Max Act: 8.4551. Min Act: -0.1700
Data Index: 2032398 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4551. Min Range: -8.4551
Max Act: 8.0176. Min Act: -0.1700
Data Index: 4853629 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.7988. Min Act: -0.1700
Data Index: 4353158 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.7676. Min Act: -0.1700
Data Index: 106159 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.7988. Min Act: -0.1700
Data Index: 2563123 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.7988. Min Act: -0.1700
Data Index: 7877021 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.7363. Min Act: -0.1700
Data Index: 3033543 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.6738. Min Act: -0.1700
Data Index: 8350161 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.6426. Min Act: -0.1700
Data Index: 5844251 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.6426. Min Act: -0.1700
Data Index: 737129 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.6426. Min Act: -0.1700
Data Index: 5415313 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.6426. Min Act: -0.1700
Data Index: 5608500 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.5801. Min Act: -0.1700
Data Index: 3468614 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.5801. Min Act: -0.1700
Data Index: 5432331 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.5488. Min Act: -0.1700
Data Index: 3504703 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.5801. Min Act: -0.1700
Data Index: 1633721 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.5176. Min Act: -0.1700
Data Index: 5872339 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.4863. Min Act: -0.1700
Data Index: 7097286 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.4863. Min Act: -0.1700
Data Index: 5133814 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.4551. Min Act: -0.1700
Data Index: 4148384 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19