Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.6067. Min Act: -0.1700
Data Index: 115469 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.5442. Min Act: -0.1700
Data Index: 5990718 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.4817. Min Act: -0.1700
Data Index: 8638502 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.4192. Min Act: -0.1700
Data Index: 3960203 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.3880. Min Act: -0.1700
Data Index: 4986759 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.3567. Min Act: -0.1700
Data Index: 7457159 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.3567. Min Act: -0.1700
Data Index: 1679731 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.3255. Min Act: -0.1700
Data Index: 6983863 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.2942. Min Act: -0.1700
Data Index: 1007155 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.2942. Min Act: -0.1700
Data Index: 7943210 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.2942. Min Act: -0.1700
Data Index: 840471 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.2942. Min Act: -0.1700
Data Index: 920712 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.2942. Min Act: -0.1700
Data Index: 1764337 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.2317. Min Act: -0.1700
Data Index: 7186584 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.2317. Min Act: -0.1700
Data Index: 3436686 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.2317. Min Act: -0.1700
Data Index: 8117125 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.2317. Min Act: -0.1700
Data Index: 4612441 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.1692. Min Act: -0.1700
Data Index: 3192855 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.1692. Min Act: -0.1700
Data Index: 942016 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6067. Min Range: -6.6067
Max Act: 6.1380. Min Act: -0.1700
Data Index: 999692 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19