Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4953. Min Range: -6.4953
Max Act: 6.4953. Min Act: -0.1700
Data Index: 4047476 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4953. Min Range: -6.4953
Max Act: 6.3703. Min Act: -0.1700
Data Index: 6633914 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4953. Min Range: -6.4953
Max Act: 6.3078. Min Act: -0.1700
Data Index: 6622768 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4953. Min Range: -6.4953
Max Act: 6.1203. Min Act: -0.1700
Data Index: 6982650 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.9953. Min Act: -0.1700
Data Index: 3002016 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.9641. Min Act: -0.1700
Data Index: 6864938 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.9641. Min Act: -0.1700
Data Index: 7360825 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.9328. Min Act: -0.1700
Data Index: 6923280 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.9016. Min Act: -0.1700
Data Index: 5692185 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.8703. Min Act: -0.1700
Data Index: 3793603 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.8703. Min Act: -0.1700
Data Index: 211525 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.8703. Min Act: -0.1700
Data Index: 7574239 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.8391. Min Act: -0.1700
Data Index: 7310454 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.7766. Min Act: -0.1700
Data Index: 3445306 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.7766. Min Act: -0.1700
Data Index: 3548471 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.7766. Min Act: -0.1700
Data Index: 5529470 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.7766. Min Act: -0.1700
Data Index: 8222871 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.7453. Min Act: -0.1700
Data Index: 6532703 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.7141. Min Act: -0.1700
Data Index: 6532715 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4953. Min Range: -6.4953
Max Act: 5.6828. Min Act: -0.1700
Data Index: 7472331 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19