Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 841 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1693. Min Range: -7.1693
Max Act: 7.1693. Min Act: -0.1700
Data Index: 8036935 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1693. Min Range: -7.1693
Max Act: 7.1381. Min Act: -0.1700
Data Index: 4894459 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.9506. Min Act: -0.1700
Data Index: 7548323 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.9506. Min Act: -0.1700
Data Index: 4543486 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.9193. Min Act: -0.1700
Data Index: 7600990 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.8881. Min Act: -0.1700
Data Index: 5359999 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.8568. Min Act: -0.1700
Data Index: 6549927 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.8568. Min Act: -0.1700
Data Index: 6660924 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7943. Min Act: -0.1700
Data Index: 1653571 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7631. Min Act: -0.1700
Data Index: 8092735 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7631. Min Act: -0.1700
Data Index: 3882282 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7318. Min Act: -0.1700
Data Index: 3420138 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7318. Min Act: -0.1700
Data Index: 646081 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7318. Min Act: -0.1700
Data Index: 6015580 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7318. Min Act: -0.1700
Data Index: 5532840 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7006. Min Act: -0.1700
Data Index: 4437699 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7006. Min Act: -0.1700
Data Index: 8658863 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7006. Min Act: -0.1700
Data Index: 5240292 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.7006. Min Act: -0.1700
Data Index: 7147876 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1693. Min Range: -7.1693
Max Act: 6.6693. Min Act: -0.1700
Data Index: 6028587 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19