Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2104 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.7828. Min Act: -0.1700
Data Index: 942514 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.5953. Min Act: -0.1700
Data Index: 758087 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.4703. Min Act: -0.1700
Data Index: 2786221 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.5328. Min Act: -0.1700
Data Index: 8244102 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.4078. Min Act: -0.1700
Data Index: 7422838 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.4078. Min Act: -0.1700
Data Index: 6876712 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.3453. Min Act: -0.1700
Data Index: 8108660 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.2828. Min Act: -0.1700
Data Index: 3655966 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.2828. Min Act: -0.1700
Data Index: 7250020 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.2203. Min Act: -0.1700
Data Index: 5109017 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.1578. Min Act: -0.1700
Data Index: 5533912 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.0953. Min Act: -0.1700
Data Index: 3346102 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.0953. Min Act: -0.1700
Data Index: 6584396 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.0953. Min Act: -0.1700
Data Index: 6959221 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.0953. Min Act: -0.1700
Data Index: 7168395 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.0328. Min Act: -0.1700
Data Index: 6114147 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.0328. Min Act: -0.1700
Data Index: 4716207 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.0328. Min Act: -0.1700
Data Index: 4153616 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.0328. Min Act: -0.1700
Data Index: 4739979 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7828. Min Range: -8.7828
Max Act: 8.0328. Min Act: -0.1700
Data Index: 1089000 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19