Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4200 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2682. Min Range: -6.2682
Max Act: 6.2682. Min Act: -0.1700
Data Index: 858273 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2682. Min Range: -6.2682
Max Act: 6.1120. Min Act: -0.1700
Data Index: 6405198 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2682. Min Range: -6.2682
Max Act: 6.1120. Min Act: -0.1700
Data Index: 977581 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2682. Min Range: -6.2682
Max Act: 6.0807. Min Act: -0.1700
Data Index: 3604251 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2682. Min Range: -6.2682
Max Act: 6.0807. Min Act: -0.1700
Data Index: 8709904 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2682. Min Range: -6.2682
Max Act: 6.0495. Min Act: -0.1700
Data Index: 3552284 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2682. Min Range: -6.2682
Max Act: 6.0182. Min Act: -0.1700
Data Index: 1542115 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.9557. Min Act: -0.1700
Data Index: 5219094 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.9245. Min Act: -0.1700
Data Index: 5636996 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.9245. Min Act: -0.1700
Data Index: 8005887 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.8620. Min Act: -0.1700
Data Index: 6605142 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.8620. Min Act: -0.1700
Data Index: 1882959 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.8620. Min Act: -0.1700
Data Index: 1719243 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.8307. Min Act: -0.1700
Data Index: 6242502 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.7995. Min Act: -0.1700
Data Index: 4999552 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.7995. Min Act: -0.1700
Data Index: 5603014 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.7682. Min Act: -0.1700
Data Index: 2944429 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.7682. Min Act: -0.1700
Data Index: 8684198 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.7682. Min Act: -0.1700
Data Index: 2676999 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2682. Min Range: -6.2682
Max Act: 5.7370. Min Act: -0.1700
Data Index: 3565662 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19