Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2800. Min Range: -10.2800
Max Act: 10.2800. Min Act: -0.1700
Data Index: 2935579 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.7800. Min Act: -0.1700
Data Index: 4916234 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.6550. Min Act: -0.1700
Data Index: 3149144 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.6550. Min Act: -0.1700
Data Index: 5629651 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.5925. Min Act: -0.1700
Data Index: 199649 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.4675. Min Act: -0.1700
Data Index: 4090356 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.5300. Min Act: -0.1700
Data Index: 733686 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.4050. Min Act: -0.1700
Data Index: 4701527 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.4675. Min Act: -0.1700
Data Index: 1230773 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.3425. Min Act: -0.1700
Data Index: 3171814 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.3425. Min Act: -0.1700
Data Index: 4665993 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.2175. Min Act: -0.1700
Data Index: 6184521 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.2800. Min Act: -0.1700
Data Index: 5102542 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.2800. Min Act: -0.1700
Data Index: 1157025 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.2175. Min Act: -0.1700
Data Index: 1659636 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.2175. Min Act: -0.1700
Data Index: 5923718 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.1550. Min Act: -0.1700
Data Index: 1370553 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.0925. Min Act: -0.1700
Data Index: 2820694 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2800. Min Range: -10.2800
Max Act: 8.9675. Min Act: -0.1700
Data Index: 480201 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2800. Min Range: -10.2800
Max Act: 9.0300. Min Act: -0.1700
Data Index: 4111872 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19