Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.7734. Min Act: -0.1700
Data Index: 3212611 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.4609. Min Act: -0.1700
Data Index: 6661872 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.3359. Min Act: -0.1700
Data Index: 3293843 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.2734. Min Act: -0.1700
Data Index: 1725787 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.2734. Min Act: -0.1700
Data Index: 3241798 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.2734. Min Act: -0.1700
Data Index: 6872831 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.1484. Min Act: -0.1700
Data Index: 3156997 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.0859. Min Act: -0.1700
Data Index: 6627067 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.0859. Min Act: -0.1700
Data Index: 6052773 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.0234. Min Act: -0.1700
Data Index: 8647020 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.0234. Min Act: -0.1700
Data Index: 5688979 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.0234. Min Act: -0.1700
Data Index: 4569003 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7734. Min Range: -10.7734
Max Act: 10.0234. Min Act: -0.1700
Data Index: 7788065 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7734. Min Range: -10.7734
Max Act: 9.9609. Min Act: -0.1700
Data Index: 8684259 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7734. Min Range: -10.7734
Max Act: 9.9609. Min Act: -0.1700
Data Index: 8272571 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7734. Min Range: -10.7734
Max Act: 9.9609. Min Act: -0.1700
Data Index: 6221726 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7734. Min Range: -10.7734
Max Act: 9.9609. Min Act: -0.1700
Data Index: 7271140 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7734. Min Range: -10.7734
Max Act: 9.9609. Min Act: -0.1700
Data Index: 3536126 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7734. Min Range: -10.7734
Max Act: 9.8984. Min Act: -0.1700
Data Index: 1272430 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7734. Min Range: -10.7734
Max Act: 9.8359. Min Act: -0.1700
Data Index: 5296917 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19