Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 11 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3603. Min Range: -7.3603
Max Act: 7.3603. Min Act: -0.1700
Data Index: 1467601 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3603. Min Range: -7.3603
Max Act: 7.2040. Min Act: -0.1700
Data Index: 8273946 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.7978. Min Act: -0.1700
Data Index: 8524691 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.7665. Min Act: -0.1700
Data Index: 2967143 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.7353. Min Act: -0.1700
Data Index: 1910209 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.6728. Min Act: -0.1700
Data Index: 5720676 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.7040. Min Act: -0.1700
Data Index: 4446574 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.6728. Min Act: -0.1700
Data Index: 852797 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.6728. Min Act: -0.1700
Data Index: 8679460 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.6103. Min Act: -0.1700
Data Index: 1026030 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.5790. Min Act: -0.1700
Data Index: 6500655 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.5790. Min Act: -0.1700
Data Index: 6941740 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.5165. Min Act: -0.1700
Data Index: 2765478 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.4853. Min Act: -0.1700
Data Index: 2008588 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.4853. Min Act: -0.1700
Data Index: 8306954 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.4853. Min Act: -0.1700
Data Index: 2484913 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.4540. Min Act: -0.1700
Data Index: 3682648 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.4540. Min Act: -0.1700
Data Index: 5632433 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.4540. Min Act: -0.1700
Data Index: 1316528 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3603. Min Range: -7.3603
Max Act: 6.4540. Min Act: -0.1700
Data Index: 629133 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19