Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4641. Min Range: -9.4641
Max Act: 9.4641. Min Act: -0.1700
Data Index: 1679021 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4641. Min Range: -9.4641
Max Act: 9.2141. Min Act: -0.1700
Data Index: 3673180 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4641. Min Range: -9.4641
Max Act: 9.0891. Min Act: -0.1700
Data Index: 1111138 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4641. Min Range: -9.4641
Max Act: 9.0266. Min Act: -0.1700
Data Index: 4141651 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4641. Min Range: -9.4641
Max Act: 9.0266. Min Act: -0.1700
Data Index: 4032222 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4641. Min Range: -9.4641
Max Act: 9.0266. Min Act: -0.1700
Data Index: 6191934 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4641. Min Range: -9.4641
Max Act: 9.0266. Min Act: -0.1700
Data Index: 8083055 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.9641. Min Act: -0.1700
Data Index: 8350975 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.9016. Min Act: -0.1700
Data Index: 720301 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.9016. Min Act: -0.1700
Data Index: 5713692 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.8391. Min Act: -0.1700
Data Index: 937329 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.8391. Min Act: -0.1700
Data Index: 3907429 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.8391. Min Act: -0.1700
Data Index: 3460263 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.8391. Min Act: -0.1700
Data Index: 7037447 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.7766. Min Act: -0.1700
Data Index: 7253312 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.7766. Min Act: -0.1700
Data Index: 446057 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.7766. Min Act: -0.1700
Data Index: 62217 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.7141. Min Act: -0.1700
Data Index: 357764 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.7141. Min Act: -0.1700
Data Index: 6426641 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4641. Min Range: -9.4641
Max Act: 8.7141. Min Act: -0.1700
Data Index: 3497507 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19