Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.6594. Min Act: -0.1700
Data Index: 524652 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.6594. Min Act: -0.1700
Data Index: 5096712 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.6594. Min Act: -0.1700
Data Index: 6096715 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.5969. Min Act: -0.1700
Data Index: 4981954 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.5344. Min Act: -0.1700
Data Index: 5697616 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.5344. Min Act: -0.1700
Data Index: 231404 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.5344. Min Act: -0.1700
Data Index: 5418270 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.5344. Min Act: -0.1700
Data Index: 2214368 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.4719. Min Act: -0.1700
Data Index: 8305829 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.4719. Min Act: -0.1700
Data Index: 5548707 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.4719. Min Act: -0.1700
Data Index: 345309 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.4719. Min Act: -0.1700
Data Index: 1569826 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.4094. Min Act: -0.1700
Data Index: 2873516 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.4094. Min Act: -0.1700
Data Index: 4993838 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.4094. Min Act: -0.1700
Data Index: 4372721 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.4094. Min Act: -0.1700
Data Index: 3726994 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.3469. Min Act: -0.1700
Data Index: 3022107 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.3469. Min Act: -0.1700
Data Index: 6177714 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.3469. Min Act: -0.1700
Data Index: 7260758 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6594. Min Range: -10.6594
Max Act: 10.2844. Min Act: -0.1700
Data Index: 6549355 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19