Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5836. Min Range: -7.5836
Max Act: 7.5836. Min Act: -0.1700
Data Index: 817443 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.9586. Min Act: -0.1700
Data Index: 333493 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.8024. Min Act: -0.1700
Data Index: 722605 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.7086. Min Act: -0.1700
Data Index: 4340813 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.6461. Min Act: -0.1700
Data Index: 4775717 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.6149. Min Act: -0.1700
Data Index: 3739835 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.5836. Min Act: -0.1700
Data Index: 7388385 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.5211. Min Act: -0.1700
Data Index: 6056852 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.4899. Min Act: -0.1700
Data Index: 6598061 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.4899. Min Act: -0.1700
Data Index: 3984752 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.4586. Min Act: -0.1700
Data Index: 4850907 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.4586. Min Act: -0.1700
Data Index: 1628636 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.4586. Min Act: -0.1700
Data Index: 5261005 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.3961. Min Act: -0.1700
Data Index: 8757433 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.3961. Min Act: -0.1700
Data Index: 2999796 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.3961. Min Act: -0.1700
Data Index: 4813618 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.3961. Min Act: -0.1700
Data Index: 6553466 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.3649. Min Act: -0.1700
Data Index: 907326 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.3649. Min Act: -0.1700
Data Index: 6158170 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5836. Min Range: -7.5836
Max Act: 6.3961. Min Act: -0.1700
Data Index: 7374106 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19