Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.8909. Min Act: -0.1700
Data Index: 6962956 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.8596. Min Act: -0.1700
Data Index: 3188816 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.7971. Min Act: -0.1700
Data Index: 1009951 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.7346. Min Act: -0.1700
Data Index: 3188821 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.7034. Min Act: -0.1700
Data Index: 3188818 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.6721. Min Act: -0.1700
Data Index: 3188822 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.6721. Min Act: -0.1700
Data Index: 3188823 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.6721. Min Act: -0.1700
Data Index: 6383542 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.6721. Min Act: -0.1700
Data Index: 4460061 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.6409. Min Act: -0.1700
Data Index: 6383532 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.6096. Min Act: -0.1700
Data Index: 3188817 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.6096. Min Act: -0.1700
Data Index: 6383543 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.5784. Min Act: -0.1700
Data Index: 3260558 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.5784. Min Act: -0.1700
Data Index: 3188824 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.5784. Min Act: -0.1700
Data Index: 3188820 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.5471. Min Act: -0.1700
Data Index: 3188819 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.5471. Min Act: -0.1700
Data Index: 1866890 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.5784. Min Act: -0.1700
Data Index: 6383531 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.5159. Min Act: -0.1700
Data Index: 6383544 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8909. Min Range: -5.8909
Max Act: 5.4846. Min Act: -0.1700
Data Index: 6383533 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19