Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 370 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0952. Min Act: -0.1700
Data Index: 4287974 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0327. Min Act: -0.1700
Data Index: 8205793 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0952. Min Act: -0.1700
Data Index: 3840543 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0327. Min Act: -0.1700
Data Index: 4287973 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0327. Min Act: -0.1700
Data Index: 5132301 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0327. Min Act: -0.1700
Data Index: 5132300 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0327. Min Act: -0.1700
Data Index: 8205794 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0952. Min Act: -0.1700
Data Index: 5857757 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0327. Min Act: -0.1700
Data Index: 3626099 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0952. Min Range: -9.0952
Max Act: 9.0327. Min Act: -0.1700
Data Index: 5857756 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.9702. Min Act: -0.1700
Data Index: 6190911 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.9702. Min Act: -0.1700
Data Index: 3213923 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.9077. Min Act: -0.1700
Data Index: 7664063 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.9077. Min Act: -0.1700
Data Index: 7878817 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.9077. Min Act: -0.1700
Data Index: 3840544 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.9077. Min Act: -0.1700
Data Index: 5484860 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.9077. Min Act: -0.1700
Data Index: 5842202 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.9077. Min Act: -0.1700
Data Index: 4651322 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.8452. Min Act: -0.1700
Data Index: 2533904 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0952. Min Range: -9.0952
Max Act: 8.9077. Min Act: -0.1700
Data Index: 3626100 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19