Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.2889. Min Act: -0.1700
Data Index: 7478334 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.2577. Min Act: -0.1700
Data Index: 4093195 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.2264. Min Act: -0.1698
Data Index: 8199971 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1639. Min Act: -0.1700
Data Index: 7303298 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1639. Min Act: -0.1700
Data Index: 1839096 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1327. Min Act: -0.1700
Data Index: 532021 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1327. Min Act: -0.1700
Data Index: 4831323 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1014. Min Act: -0.1700
Data Index: 754006 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1014. Min Act: -0.1700
Data Index: 8555088 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.0702. Min Act: -0.1700
Data Index: 8770980 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1014. Min Act: -0.1700
Data Index: 3978078 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1014. Min Act: -0.1700
Data Index: 1520014 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1014. Min Act: -0.1700
Data Index: 7047552 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1014. Min Act: -0.1700
Data Index: 4466500 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1014. Min Act: -0.1700
Data Index: 2822059 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1014. Min Act: -0.1700
Data Index: 2869802 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.1014. Min Act: -0.1700
Data Index: 2655539 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.0702. Min Act: -0.1700
Data Index: 6914590 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.0702. Min Act: -0.1700
Data Index: 3656880 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2889. Min Range: -5.2889
Max Act: 5.0702. Min Act: -0.1700
Data Index: 626759 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19