Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.8930. Min Act: -0.1700
Data Index: 3941266 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.6430. Min Act: -0.1700
Data Index: 7506469 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.6430. Min Act: -0.1700
Data Index: 1089861 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.6430. Min Act: -0.1700
Data Index: 2110972 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.5805. Min Act: -0.1700
Data Index: 5173458 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.5180. Min Act: -0.1700
Data Index: 4722268 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.4555. Min Act: -0.1700
Data Index: 3622789 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.4555. Min Act: -0.1700
Data Index: 5243528 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.4555. Min Act: -0.1700
Data Index: 8282773 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.3930. Min Act: -0.1700
Data Index: 6449836 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.3930. Min Act: -0.1700
Data Index: 8246834 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.3305. Min Act: -0.1700
Data Index: 4677025 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.3305. Min Act: -0.1700
Data Index: 4867339 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.2055. Min Act: -0.1700
Data Index: 4257298 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.2680. Min Act: -0.1700
Data Index: 8123948 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.2680. Min Act: -0.1700
Data Index: 2903256 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.2055. Min Act: -0.1700
Data Index: 3119025 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.2055. Min Act: -0.1700
Data Index: 5134281 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.2055. Min Act: -0.1700
Data Index: 187921 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8930. Min Range: -8.8930
Max Act: 8.2680. Min Act: -0.1699
Data Index: 6315187 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19