Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4954 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.5488. Min Act: -0.1700
Data Index: 8422916 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.4238. Min Act: -0.1700
Data Index: 4250606 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.3926. Min Act: -0.1700
Data Index: 1106931 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.2051. Min Act: -0.1700
Data Index: 4794575 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.1426. Min Act: -0.1700
Data Index: 1450663 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.1426. Min Act: -0.1700
Data Index: 5605815 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.1113. Min Act: -0.1700
Data Index: 4961954 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.1113. Min Act: -0.1700
Data Index: 7735055 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.1113. Min Act: -0.1700
Data Index: 184014 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.1738. Min Act: -0.1700
Data Index: 3736574 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.0801. Min Act: -0.1700
Data Index: 6865889 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.1113. Min Act: -0.1700
Data Index: 5125622 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.1113. Min Act: -0.1700
Data Index: 8301114 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.0488. Min Act: -0.1700
Data Index: 8082260 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.0488. Min Act: -0.1700
Data Index: 3574162 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.0801. Min Act: -0.1700
Data Index: 1202325 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5488. Min Range: -7.5488
Max Act: 6.9863. Min Act: -0.1700
Data Index: 4061704 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5488. Min Range: -7.5488
Max Act: 7.0488. Min Act: -0.1700
Data Index: 2036252 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5488. Min Range: -7.5488
Max Act: 6.9863. Min Act: -0.1700
Data Index: 3390262 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5488. Min Range: -7.5488
Max Act: 6.9551. Min Act: -0.1700
Data Index: 6438287 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19