Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2074 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.6251. Min Act: -0.1700
Data Index: 3008055 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5781. Min Act: -0.1700
Data Index: 928120 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5311. Min Act: -0.1700
Data Index: 4509705 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5625. Min Act: -0.1700
Data Index: 1896133 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5468. Min Act: -0.1700
Data Index: 88399 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5311. Min Act: -0.1700
Data Index: 4483786 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5311. Min Act: -0.1700
Data Index: 6129327 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5468. Min Act: -0.1700
Data Index: 409850 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.4998. Min Act: -0.1700
Data Index: 6239953 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5311. Min Act: -0.1700
Data Index: 509483 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5155. Min Act: -0.1700
Data Index: 3804399 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5155. Min Act: -0.1700
Data Index: 8606574 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.4998. Min Act: -0.1700
Data Index: 3884383 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.4998. Min Act: -0.1700
Data Index: 2520204 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.5155. Min Act: -0.1700
Data Index: 5920329 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.4842. Min Act: -0.1700
Data Index: 7826940 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.4842. Min Act: -0.1700
Data Index: 2442730 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.4528. Min Act: -0.1700
Data Index: 6068323 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.4685. Min Act: -0.1700
Data Index: 7605049 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6251. Min Range: -3.6251
Max Act: 3.4685. Min Act: -0.1700
Data Index: 8185628 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19