Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1897 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4280. Min Range: -6.4280
Max Act: 6.4280. Min Act: -0.1700
Data Index: 8026127 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4280. Min Range: -6.4280
Max Act: 6.2717. Min Act: -0.1700
Data Index: 1745313 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4280. Min Range: -6.4280
Max Act: 6.1780. Min Act: -0.1700
Data Index: 6859226 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4280. Min Range: -6.4280
Max Act: 6.0530. Min Act: -0.1700
Data Index: 5455892 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4280. Min Range: -6.4280
Max Act: 6.0217. Min Act: -0.1700
Data Index: 2625617 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.9905. Min Act: -0.1700
Data Index: 8662047 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.9592. Min Act: -0.1700
Data Index: 7620687 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.8967. Min Act: -0.1700
Data Index: 999556 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.8655. Min Act: -0.1700
Data Index: 4551222 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.8655. Min Act: -0.1700
Data Index: 5228964 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.8655. Min Act: -0.1700
Data Index: 4979341 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.8030. Min Act: -0.1700
Data Index: 7184878 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.8030. Min Act: -0.1700
Data Index: 7620686 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.8030. Min Act: -0.1700
Data Index: 7424973 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.7092. Min Act: -0.1700
Data Index: 3425785 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.6467. Min Act: -0.1700
Data Index: 812558 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.6780. Min Act: -0.1700
Data Index: 6819017 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.6467. Min Act: -0.1700
Data Index: 4190041 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.6780. Min Act: -0.1700
Data Index: 3884483 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4280. Min Range: -6.4280
Max Act: 5.6780. Min Act: -0.1700
Data Index: 3169615 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19