Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5799 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.6901. Min Act: -0.1700
Data Index: 3392881 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.5963. Min Act: -0.1700
Data Index: 318321 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.5026. Min Act: -0.1700
Data Index: 364382 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.5026. Min Act: -0.1700
Data Index: 5628020 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.3151. Min Act: -0.1700
Data Index: 6480327 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.2838. Min Act: -0.1700
Data Index: 428222 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.2838. Min Act: -0.1700
Data Index: 1242059 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.2213. Min Act: -0.1700
Data Index: 5662611 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.1901. Min Act: -0.1700
Data Index: 5594055 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.1901. Min Act: -0.1700
Data Index: 98808 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.1276. Min Act: -0.1700
Data Index: 7662322 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.1276. Min Act: -0.1700
Data Index: 2410031 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.1276. Min Act: -0.1700
Data Index: 4921836 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.0338. Min Act: -0.1700
Data Index: 4350799 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.0651. Min Act: -0.1700
Data Index: 2552080 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.0651. Min Act: -0.1700
Data Index: 803513 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.0338. Min Act: -0.1700
Data Index: 4151641 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.0338. Min Act: -0.1700
Data Index: 5594054 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.0338. Min Act: -0.1700
Data Index: 5837646 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6901. Min Range: -7.6901
Max Act: 7.0026. Min Act: -0.1700
Data Index: 4131158 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19