Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1582 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.3785. Min Act: -0.1700
Data Index: 2881909 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.3160. Min Act: -0.1700
Data Index: 1095181 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.3160. Min Act: -0.1700
Data Index: 7175529 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2847. Min Act: -0.1700
Data Index: 3233363 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2222. Min Act: -0.1700
Data Index: 3698388 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2535. Min Act: -0.1700
Data Index: 5865391 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2535. Min Act: -0.1700
Data Index: 4791249 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2222. Min Act: -0.1700
Data Index: 5397810 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2222. Min Act: -0.1700
Data Index: 83965 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2222. Min Act: -0.1700
Data Index: 5622569 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 2741736 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2222. Min Act: -0.1700
Data Index: 1080496 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 6355679 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2222. Min Act: -0.1700
Data Index: 7291416 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 3397629 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1597. Min Act: -0.1700
Data Index: 4380561 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 6905812 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1597. Min Act: -0.1700
Data Index: 1871091 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1597. Min Act: -0.1700
Data Index: 6983351 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1597. Min Act: -0.1700
Data Index: 4934317 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19