Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.9182. Min Act: -0.1700
Data Index: 6162758 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.6995. Min Act: -0.1700
Data Index: 2660508 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.6682. Min Act: -0.1700
Data Index: 4992892 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.6370. Min Act: -0.1700
Data Index: 1546357 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.6370. Min Act: -0.1700
Data Index: 1188962 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.6057. Min Act: -0.1700
Data Index: 8471537 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5745. Min Act: -0.1700
Data Index: 6088022 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5745. Min Act: -0.1700
Data Index: 8494156 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5432. Min Act: -0.1700
Data Index: 1050793 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5432. Min Act: -0.1700
Data Index: 6400929 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.4807. Min Act: -0.1700
Data Index: 545555 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5120. Min Act: -0.1700
Data Index: 7167111 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5120. Min Act: -0.1700
Data Index: 5174012 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5120. Min Act: -0.1700
Data Index: 3519088 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5120. Min Act: -0.1700
Data Index: 6145196 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5120. Min Act: -0.1700
Data Index: 1708691 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.5120. Min Act: -0.1700
Data Index: 5442771 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.4807. Min Act: -0.1700
Data Index: 5246025 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.4807. Min Act: -0.1700
Data Index: 2010743 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9182. Min Range: -5.9182
Max Act: 5.4495. Min Act: -0.1700
Data Index: 4058841 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19