Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.3502. Min Act: -0.1700
Data Index: 6952738 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.2252. Min Act: -0.1700
Data Index: 7906163 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3502. Min Range: -6.3502
Max Act: 6.0690. Min Act: -0.1700
Data Index: 7680565 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.8502. Min Act: -0.1700
Data Index: 6215168 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.8502. Min Act: -0.1700
Data Index: 7736122 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.8502. Min Act: -0.1700
Data Index: 8261871 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.8190. Min Act: -0.1700
Data Index: 942821 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7877. Min Act: -0.1700
Data Index: 8410578 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7877. Min Act: -0.1700
Data Index: 6323485 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7565. Min Act: -0.1700
Data Index: 792553 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.6940. Min Act: -0.1700
Data Index: 2598699 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7252. Min Act: -0.1700
Data Index: 3510200 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7252. Min Act: -0.1700
Data Index: 3465493 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7565. Min Act: -0.1700
Data Index: 8535294 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7252. Min Act: -0.1700
Data Index: 5289161 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7252. Min Act: -0.1700
Data Index: 6514320 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7252. Min Act: -0.1700
Data Index: 2200105 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.7252. Min Act: -0.1700
Data Index: 4623087 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.6627. Min Act: -0.1700
Data Index: 7354116 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3502. Min Range: -6.3502
Max Act: 5.6940. Min Act: -0.1700
Data Index: 5768578 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19