Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 335 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.4737. Min Act: -0.1700
Data Index: 4107606 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.4112. Min Act: -0.1700
Data Index: 215325 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.4425. Min Act: -0.1700
Data Index: 916589 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.2550. Min Act: -0.1700
Data Index: 1068292 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.1925. Min Act: -0.1700
Data Index: 3325688 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.1300. Min Act: -0.1700
Data Index: 5962914 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.1612. Min Act: -0.1700
Data Index: 6910718 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.1300. Min Act: -0.1700
Data Index: 6798379 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.1300. Min Act: -0.1700
Data Index: 1712307 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.1300. Min Act: -0.1700
Data Index: 3161865 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0987. Min Act: -0.1700
Data Index: 4084057 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0675. Min Act: -0.1700
Data Index: 8658288 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0675. Min Act: -0.1700
Data Index: 3671985 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0675. Min Act: -0.1700
Data Index: 174060 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0675. Min Act: -0.1700
Data Index: 4397474 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0675. Min Act: -0.1700
Data Index: 6053131 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0675. Min Act: -0.1700
Data Index: 8751182 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0362. Min Act: -0.1700
Data Index: 7867399 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0675. Min Act: -0.1700
Data Index: 5782368 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4737. Min Range: -5.4737
Max Act: 5.0675. Min Act: -0.1700
Data Index: 8108872 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19