Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1647 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0032. Min Range: -5.0032
Max Act: 5.0032. Min Act: -0.1700
Data Index: 4066244 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.9720. Min Act: -0.1700
Data Index: 7535367 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.9407. Min Act: -0.1700
Data Index: 5274861 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.8782. Min Act: -0.1700
Data Index: 3032312 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.7845. Min Act: -0.1700
Data Index: 1388473 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.7532. Min Act: -0.1700
Data Index: 4569344 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.7220. Min Act: -0.1700
Data Index: 1466526 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.6595. Min Act: -0.1700
Data Index: 1466527 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.6282. Min Act: -0.1700
Data Index: 1466525 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.6595. Min Act: -0.1700
Data Index: 4578523 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.5970. Min Act: -0.1700
Data Index: 1466540 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.5657. Min Act: -0.1700
Data Index: 4066240 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.5657. Min Act: -0.1700
Data Index: 211374 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.5032. Min Act: -0.1700
Data Index: 4066247 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.5032. Min Act: -0.1700
Data Index: 5488295 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.5032. Min Act: -0.1700
Data Index: 1231570 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.5032. Min Act: -0.1700
Data Index: 3032311 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.4720. Min Act: -0.1700
Data Index: 4277440 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.4720. Min Act: -0.1700
Data Index: 1299667 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0032. Min Range: -5.0032
Max Act: 4.4095. Min Act: -0.1700
Data Index: 702950 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19