Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.6923. Min Act: -0.1700
Data Index: 513227 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.5673. Min Act: -0.1700
Data Index: 6630478 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.4423. Min Act: -0.1700
Data Index: 198728 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.1923. Min Act: -0.1700
Data Index: 4700457 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.1611. Min Act: -0.1700
Data Index: 6086002 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.0673. Min Act: -0.1700
Data Index: 4262846 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.0673. Min Act: -0.1700
Data Index: 2928391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.0673. Min Act: -0.1700
Data Index: 149783 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.0673. Min Act: -0.1700
Data Index: 4002365 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.0360. Min Act: -0.1700
Data Index: 6435217 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.0360. Min Act: -0.1700
Data Index: 2022623 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.0360. Min Act: -0.1700
Data Index: 8756360 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.0048. Min Act: -0.1700
Data Index: 7137657 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6923. Min Range: -4.6923
Max Act: 4.0048. Min Act: -0.1700
Data Index: 4403998 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6923. Min Range: -4.6923
Max Act: 3.9735. Min Act: -0.1700
Data Index: 444979 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6923. Min Range: -4.6923
Max Act: 3.9735. Min Act: -0.1700
Data Index: 1202896 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6923. Min Range: -4.6923
Max Act: 3.9735. Min Act: -0.1700
Data Index: 4934246 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6923. Min Range: -4.6923
Max Act: 3.9735. Min Act: -0.1700
Data Index: 3961363 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6923. Min Range: -4.6923
Max Act: 3.9735. Min Act: -0.1700
Data Index: 2505723 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6923. Min Range: -4.6923
Max Act: 3.9735. Min Act: -0.1700
Data Index: 2029894 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19