Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5967 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8743. Min Range: -9.8743
Max Act: 9.8743. Min Act: -0.1700
Data Index: 8343306 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8743. Min Range: -9.8743
Max Act: 9.7493. Min Act: -0.1700
Data Index: 404184 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8743. Min Range: -9.8743
Max Act: 9.5618. Min Act: -0.1700
Data Index: 3163650 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8743. Min Range: -9.8743
Max Act: 9.1868. Min Act: -0.1700
Data Index: 6867823 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8743. Min Range: -9.8743
Max Act: 9.1868. Min Act: -0.1700
Data Index: 1388026 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8743. Min Range: -9.8743
Max Act: 9.1868. Min Act: -0.1700
Data Index: 7017159 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8743. Min Range: -9.8743
Max Act: 9.1243. Min Act: -0.1700
Data Index: 7925098 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.9993. Min Act: -0.1700
Data Index: 2280886 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.9993. Min Act: -0.1700
Data Index: 8525369 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.9993. Min Act: -0.1700
Data Index: 2816978 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.9993. Min Act: -0.1700
Data Index: 3490757 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.9993. Min Act: -0.1700
Data Index: 2335621 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.9368. Min Act: -0.1700
Data Index: 241028 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.8743. Min Act: -0.1700
Data Index: 6287993 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.7493. Min Act: -0.1700
Data Index: 1997799 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.7493. Min Act: -0.1700
Data Index: 3102812 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.7493. Min Act: -0.1700
Data Index: 3234974 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.7493. Min Act: -0.1700
Data Index: 974269 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.6868. Min Act: -0.1700
Data Index: 4149852 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8743. Min Range: -9.8743
Max Act: 8.7493. Min Act: -0.1700
Data Index: 7931030 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19