Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0613. Min Range: -6.0613
Max Act: 6.0613. Min Act: -0.1700
Data Index: 6135255 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.5613. Min Act: -0.1700
Data Index: 7535777 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.4363. Min Act: -0.1700
Data Index: 7940263 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.4363. Min Act: -0.1700
Data Index: 3899615 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.4051. Min Act: -0.1700
Data Index: 701769 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.3738. Min Act: -0.1700
Data Index: 4846125 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.3738. Min Act: -0.1700
Data Index: 1188585 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.3426. Min Act: -0.1700
Data Index: 6792567 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.3426. Min Act: -0.1700
Data Index: 6843495 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.3113. Min Act: -0.1700
Data Index: 8309392 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.3113. Min Act: -0.1700
Data Index: 2699441 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.2801. Min Act: -0.1700
Data Index: 1807496 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.2801. Min Act: -0.1700
Data Index: 1125 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.2801. Min Act: -0.1700
Data Index: 8271133 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.2488. Min Act: -0.1700
Data Index: 371433 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.2176. Min Act: -0.1700
Data Index: 5679102 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.2176. Min Act: -0.1700
Data Index: 1396746 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.2176. Min Act: -0.1700
Data Index: 2705132 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.2176. Min Act: -0.1700
Data Index: 6947545 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0613. Min Range: -6.0613
Max Act: 5.1863. Min Act: -0.1700
Data Index: 379787 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19