Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 448 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.3728. Min Act: -0.1700
Data Index: 1374712 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.0916. Min Act: -0.1700
Data Index: 3654339 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.1228. Min Act: -0.1700
Data Index: 8427222 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.0291. Min Act: -0.1700
Data Index: 7464613 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.0916. Min Act: -0.1700
Data Index: 7001946 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.0603. Min Act: -0.1700
Data Index: 3754807 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.0291. Min Act: -0.1700
Data Index: 3925423 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9978. Min Act: -0.1700
Data Index: 8304131 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.0291. Min Act: -0.1700
Data Index: 8291963 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9978. Min Act: -0.1700
Data Index: 3697910 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9666. Min Act: -0.1700
Data Index: 2313732 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9353. Min Act: -0.1700
Data Index: 3935980 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9353. Min Act: -0.1700
Data Index: 2787009 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9041. Min Act: -0.1700
Data Index: 3155856 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9041. Min Act: -0.1700
Data Index: 4682908 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9041. Min Act: -0.1700
Data Index: 8524753 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.8416. Min Act: -0.1700
Data Index: 4049391 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.8416. Min Act: -0.1700
Data Index: 5779505 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.8416. Min Act: -0.1700
Data Index: 3726235 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.7791. Min Act: -0.1700
Data Index: 6761582 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19