Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1391 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.6756. Min Act: -0.1700
Data Index: 1038609 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.5506. Min Act: -0.1700
Data Index: 6226058 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.5506. Min Act: -0.1700
Data Index: 1578514 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.5506. Min Act: -0.1700
Data Index: 240077 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.4569. Min Act: -0.1700
Data Index: 5112759 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.4569. Min Act: -0.1700
Data Index: 7184292 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.3944. Min Act: -0.1700
Data Index: 1484036 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.3631. Min Act: -0.1700
Data Index: 6899613 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.3631. Min Act: -0.1700
Data Index: 6129662 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.3631. Min Act: -0.1700
Data Index: 5707898 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.3319. Min Act: -0.1700
Data Index: 5707894 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.3006. Min Act: -0.1700
Data Index: 8711863 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.2694. Min Act: -0.1700
Data Index: 7161473 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.3006. Min Act: -0.1700
Data Index: 3227764 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.3006. Min Act: -0.1700
Data Index: 3467643 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.2694. Min Act: -0.1700
Data Index: 4866757 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.2694. Min Act: -0.1700
Data Index: 5353322 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.2694. Min Act: -0.1700
Data Index: 2195947 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.2694. Min Act: -0.1700
Data Index: 1919660 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6756. Min Range: -6.6756
Max Act: 6.2381. Min Act: -0.1700
Data Index: 2456068 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19