Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1096. Min Range: -8.1096
Max Act: 8.1096. Min Act: -0.1699
Data Index: 4435486 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.9846. Min Act: -0.1700
Data Index: 3689282 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.9221. Min Act: -0.1700
Data Index: 3197806 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.8596. Min Act: -0.1700
Data Index: 762787 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.7971. Min Act: -0.1700
Data Index: 5442242 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.7971. Min Act: -0.1700
Data Index: 557393 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.6721. Min Act: -0.1700
Data Index: 1370742 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.6409. Min Act: -0.1700
Data Index: 4015673 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.6096. Min Act: -0.1700
Data Index: 3482004 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.6096. Min Act: -0.1700
Data Index: 7572002 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.6409. Min Act: -0.1700
Data Index: 6570498 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.5784. Min Act: -0.1700
Data Index: 3087456 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.5784. Min Act: -0.1700
Data Index: 6477098 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.5784. Min Act: -0.1700
Data Index: 8336967 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.5471. Min Act: -0.1700
Data Index: 4845437 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.5471. Min Act: -0.1700
Data Index: 8061422 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.5784. Min Act: -0.1700
Data Index: 5539612 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.5159. Min Act: -0.1700
Data Index: 3369664 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.5471. Min Act: -0.1700
Data Index: 3563768 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1096. Min Range: -8.1096
Max Act: 7.5159. Min Act: -0.1700
Data Index: 6153913 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19