Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4855 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.7829. Min Act: -0.1700
Data Index: 7444602 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.7204. Min Act: -0.1700
Data Index: 5271779 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.6891. Min Act: -0.1700
Data Index: 1380519 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.6266. Min Act: -0.1700
Data Index: 5759044 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.6266. Min Act: -0.1700
Data Index: 4357062 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.6579. Min Act: -0.1700
Data Index: 4646287 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.6579. Min Act: -0.1700
Data Index: 2571037 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5954. Min Act: -0.1700
Data Index: 3306021 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5954. Min Act: -0.1700
Data Index: 1636061 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.6266. Min Act: -0.1700
Data Index: 4973 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5641. Min Act: -0.1700
Data Index: 3435564 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5329. Min Act: -0.1700
Data Index: 321631 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5329. Min Act: -0.1700
Data Index: 340118 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5329. Min Act: -0.1700
Data Index: 3078928 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.4704. Min Act: -0.1700
Data Index: 1833786 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5016. Min Act: -0.1700
Data Index: 6096414 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5016. Min Act: -0.1700
Data Index: 64157 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5016. Min Act: -0.1700
Data Index: 1833784 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.4704. Min Act: -0.1700
Data Index: 8410209 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7829. Min Range: -5.7829
Max Act: 5.5016. Min Act: -0.1700
Data Index: 5065887 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19