Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2217 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.6762. Min Act: -0.1700
Data Index: 5846834 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.4887. Min Act: -0.1700
Data Index: 8583505 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.4887. Min Act: -0.1700
Data Index: 707989 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.4262. Min Act: -0.1700
Data Index: 5635373 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.2075. Min Act: -0.1700
Data Index: 2318411 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.2075. Min Act: -0.1700
Data Index: 5250529 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.1762. Min Act: -0.1700
Data Index: 6373560 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.1762. Min Act: -0.1700
Data Index: 2149242 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.2075. Min Act: -0.1700
Data Index: 3084456 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.1450. Min Act: -0.1700
Data Index: 250320 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.1137. Min Act: -0.1700
Data Index: 6669466 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.0512. Min Act: -0.1700
Data Index: 8019786 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.0825. Min Act: -0.1700
Data Index: 3070917 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.0825. Min Act: -0.1700
Data Index: 1598048 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.0512. Min Act: -0.1700
Data Index: 5343107 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.0512. Min Act: -0.1700
Data Index: 5833705 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.0200. Min Act: -0.1700
Data Index: 2320911 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6762. Min Range: -7.6762
Max Act: 7.0512. Min Act: -0.1700
Data Index: 4075214 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6762. Min Range: -7.6762
Max Act: 6.9887. Min Act: -0.1700
Data Index: 2698189 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6762. Min Range: -7.6762
Max Act: 6.9887. Min Act: -0.1700
Data Index: 3430661 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19