Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 878 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0559. Min Range: -6.0559
Max Act: 6.0559. Min Act: -0.1700
Data Index: 7097343 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.9309. Min Act: -0.1700
Data Index: 3088422 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.8684. Min Act: -0.1700
Data Index: 5961275 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.7746. Min Act: -0.1700
Data Index: 7776746 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.7121. Min Act: -0.1700
Data Index: 2329092 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.7434. Min Act: -0.1700
Data Index: 3101041 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.7121. Min Act: -0.1700
Data Index: 714771 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.7121. Min Act: -0.1700
Data Index: 7398046 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.6184. Min Act: -0.1700
Data Index: 7250491 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.5871. Min Act: -0.1700
Data Index: 8601537 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.5871. Min Act: -0.1700
Data Index: 6484172 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.4934. Min Act: -0.1700
Data Index: 7973323 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.4934. Min Act: -0.1700
Data Index: 3818528 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.4621. Min Act: -0.1700
Data Index: 8200629 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.4621. Min Act: -0.1700
Data Index: 3818529 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.4621. Min Act: -0.1700
Data Index: 4841777 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.4309. Min Act: -0.1700
Data Index: 4884601 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.4309. Min Act: -0.1700
Data Index: 5087947 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.4309. Min Act: -0.1700
Data Index: 5087546 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0559. Min Range: -6.0559
Max Act: 5.3996. Min Act: -0.1700
Data Index: 235752 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19