Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1005 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.4977. Min Act: -0.1700
Data Index: 8033692 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.4977. Min Act: -0.1700
Data Index: 3329412 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.4664. Min Act: -0.1700
Data Index: 5007845 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.4664. Min Act: -0.1700
Data Index: 1619560 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.4664. Min Act: -0.1700
Data Index: 3111141 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.4352. Min Act: -0.1700
Data Index: 3940884 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.4039. Min Act: -0.1700
Data Index: 2366887 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.4039. Min Act: -0.1700
Data Index: 6003849 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3727. Min Act: -0.1700
Data Index: 1925012 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3727. Min Act: -0.1700
Data Index: 2589917 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3727. Min Act: -0.1700
Data Index: 1202685 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3414. Min Act: -0.1700
Data Index: 7161041 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3414. Min Act: -0.1700
Data Index: 6979168 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3414. Min Act: -0.1700
Data Index: 6642457 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3414. Min Act: -0.1700
Data Index: 2841337 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3414. Min Act: -0.1700
Data Index: 6594939 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3414. Min Act: -0.1700
Data Index: 6005740 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3414. Min Act: -0.1700
Data Index: 5872774 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3414. Min Act: -0.1700
Data Index: 524675 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4977. Min Range: -5.4977
Max Act: 5.3414. Min Act: -0.1700
Data Index: 5815567 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19