Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2513 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0875. Min Range: -10.0875
Max Act: 10.0875. Min Act: -0.1700
Data Index: 3161905 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0875. Min Range: -10.0875
Max Act: 10.0875. Min Act: -0.1700
Data Index: 4372300 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.7125. Min Act: -0.1700
Data Index: 8332301 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.6500. Min Act: -0.1700
Data Index: 7925551 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.5875. Min Act: -0.1700
Data Index: 4901753 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.5250. Min Act: -0.1700
Data Index: 409390 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.4625. Min Act: -0.1700
Data Index: 101571 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.4000. Min Act: -0.1700
Data Index: 4933020 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.4000. Min Act: -0.1700
Data Index: 5243157 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.2750. Min Act: -0.1700
Data Index: 3570883 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.2750. Min Act: -0.1700
Data Index: 4469407 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.2750. Min Act: -0.1700
Data Index: 4314884 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.2750. Min Act: -0.1700
Data Index: 4846654 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.2750. Min Act: -0.1700
Data Index: 7789941 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.2125. Min Act: -0.1700
Data Index: 5370004 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.2125. Min Act: -0.1700
Data Index: 5840675 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.1500. Min Act: -0.1700
Data Index: 6590694 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.1500. Min Act: -0.1700
Data Index: 7151698 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.1500. Min Act: -0.1700
Data Index: 3690950 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0875. Min Range: -10.0875
Max Act: 9.1500. Min Act: -0.1700
Data Index: 3330097 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19