Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.5924. Min Act: -0.1700
Data Index: 1783790 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.5924. Min Act: -0.1700
Data Index: 5251111 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.5299. Min Act: -0.1700
Data Index: 7104862 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.4987. Min Act: -0.1700
Data Index: 444787 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.4987. Min Act: -0.1700
Data Index: 328468 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.4674. Min Act: -0.1700
Data Index: 1050350 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.4362. Min Act: -0.1700
Data Index: 4634987 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.4362. Min Act: -0.1700
Data Index: 1088742 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.4362. Min Act: -0.1700
Data Index: 2456959 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.4049. Min Act: -0.1700
Data Index: 1050351 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.3112. Min Act: -0.1700
Data Index: 7564324 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.2799. Min Act: -0.1700
Data Index: 3479398 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.1862. Min Act: -0.1700
Data Index: 8518758 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.1237. Min Act: -0.1700
Data Index: 703418 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.0924. Min Act: -0.1700
Data Index: 4634982 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.0612. Min Act: -0.1700
Data Index: 2779652 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5924. Min Range: -5.5924
Max Act: 5.0612. Min Act: -0.1700
Data Index: 1708670 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5924. Min Range: -5.5924
Max Act: 4.9987. Min Act: -0.1700
Data Index: 5491283 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5924. Min Range: -5.5924
Max Act: 4.9987. Min Act: -0.1700
Data Index: 5007922 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5924. Min Range: -5.5924
Max Act: 4.9049. Min Act: -0.1700
Data Index: 445658 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19