Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2653 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2317. Min Range: -7.2317
Max Act: 7.2317. Min Act: -0.1700
Data Index: 4795432 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2317. Min Range: -7.2317
Max Act: 7.1067. Min Act: -0.1700
Data Index: 3036768 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2317. Min Range: -7.2317
Max Act: 7.0442. Min Act: -0.1700
Data Index: 7816793 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.9817. Min Act: -0.1700
Data Index: 7837919 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.7942. Min Act: -0.1700
Data Index: 2775225 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.7317. Min Act: -0.1700
Data Index: 8421713 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.7317. Min Act: -0.1700
Data Index: 4429157 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.7317. Min Act: -0.1700
Data Index: 514178 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.6692. Min Act: -0.1700
Data Index: 800948 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.6692. Min Act: -0.1700
Data Index: 7081426 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.6692. Min Act: -0.1700
Data Index: 6428798 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.6067. Min Act: -0.1700
Data Index: 1994841 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.6067. Min Act: -0.1700
Data Index: 1637674 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.6067. Min Act: -0.1700
Data Index: 800949 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.6067. Min Act: -0.1700
Data Index: 1969472 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.6067. Min Act: -0.1700
Data Index: 4394964 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.5442. Min Act: -0.1700
Data Index: 1969470 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.5442. Min Act: -0.1700
Data Index: 6789235 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.5442. Min Act: -0.1700
Data Index: 2767218 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2317. Min Range: -7.2317
Max Act: 6.5442. Min Act: -0.1700
Data Index: 2590734 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19