Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1728 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.5777. Min Act: -0.1700
Data Index: 2026757 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.5152. Min Act: -0.1700
Data Index: 4948817 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.3589. Min Act: -0.1700
Data Index: 5343016 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.3589. Min Act: -0.1700
Data Index: 5914460 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.3277. Min Act: -0.1700
Data Index: 1402579 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.2652. Min Act: -0.1700
Data Index: 412662 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.2027. Min Act: -0.1700
Data Index: 8569899 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.2027. Min Act: -0.1700
Data Index: 269223 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.2027. Min Act: -0.1700
Data Index: 8308310 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.2027. Min Act: -0.1700
Data Index: 2828043 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.2027. Min Act: -0.1700
Data Index: 5056945 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.2027. Min Act: -0.1700
Data Index: 886765 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.2027. Min Act: -0.1700
Data Index: 473895 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.1714. Min Act: -0.1700
Data Index: 7870804 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.1714. Min Act: -0.1700
Data Index: 7378759 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.1714. Min Act: -0.1700
Data Index: 1112337 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.1089. Min Act: -0.1700
Data Index: 3772566 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.1089. Min Act: -0.1700
Data Index: 7047073 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.1089. Min Act: -0.1700
Data Index: 2504524 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5777. Min Range: -5.5777
Max Act: 5.0777. Min Act: -0.1700
Data Index: 3344399 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19