Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4865 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0678. Min Range: -1.0678
Max Act: 1.0678. Min Act: -0.1700
Data Index: 8418630 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.9895. Min Act: -0.1698
Data Index: 8178764 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.9635. Min Act: -0.1700
Data Index: 2924352 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.9033. Min Act: -0.1700
Data Index: 3476364 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8948. Min Act: -0.1696
Data Index: 7152164 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8948. Min Act: -0.1696
Data Index: 4699564 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8777. Min Act: -0.1697
Data Index: 2535385 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8863. Min Act: -0.1696
Data Index: 3894617 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8777. Min Act: -0.1700
Data Index: 5052890 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8777. Min Act: -0.1669
Data Index: 3560764 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8607. Min Act: -0.1700
Data Index: 2827653 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8692. Min Act: -0.1700
Data Index: 7357885 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8692. Min Act: -0.1699
Data Index: 5022953 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8607. Min Act: -0.1700
Data Index: 7646133 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8438. Min Act: -0.1700
Data Index: 2341880 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8522. Min Act: -0.1700
Data Index: 7843582 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8438. Min Act: -0.1700
Data Index: 8092403 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8353. Min Act: -0.1685
Data Index: 7262249 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8353. Min Act: -0.1700
Data Index: 3959506 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0678. Min Range: -1.0678
Max Act: 0.8522. Min Act: -0.1700
Data Index: 6614646 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19