Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 979 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.5109. Min Act: -0.1700
Data Index: 7759993 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.4172. Min Act: -0.1700
Data Index: 6588359 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.2922. Min Act: -0.1700
Data Index: 4228233 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.2609. Min Act: -0.1700
Data Index: 3542835 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.2609. Min Act: -0.1700
Data Index: 5854434 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.2297. Min Act: -0.1700
Data Index: 5235917 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.1984. Min Act: -0.1700
Data Index: 1891793 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.2297. Min Act: -0.1700
Data Index: 588082 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.1984. Min Act: -0.1700
Data Index: 7015009 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.1984. Min Act: -0.1700
Data Index: 2323865 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.1672. Min Act: -0.1700
Data Index: 2173745 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.1047. Min Act: -0.1700
Data Index: 8131843 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.1359. Min Act: -0.1700
Data Index: 2902987 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.1047. Min Act: -0.1700
Data Index: 5275530 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.0734. Min Act: -0.1700
Data Index: 1805953 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.0422. Min Act: -0.1700
Data Index: 5283047 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5109. Min Range: -7.5109
Max Act: 7.0109. Min Act: -0.1700
Data Index: 4009413 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5109. Min Range: -7.5109
Max Act: 6.9797. Min Act: -0.1700
Data Index: 1277504 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5109. Min Range: -7.5109
Max Act: 6.9797. Min Act: -0.1700
Data Index: 8029778 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5109. Min Range: -7.5109
Max Act: 6.9797. Min Act: -0.1700
Data Index: 6378440 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19