Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.6606. Min Act: -0.1700
Data Index: 7036018 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.4727. Min Act: -0.1700
Data Index: 8244680 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.3630. Min Act: -0.1700
Data Index: 2042969 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.3630. Min Act: -0.1700
Data Index: 7575054 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.3473. Min Act: -0.1700
Data Index: 5694915 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.3316. Min Act: -0.1700
Data Index: 8506492 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.3002. Min Act: -0.1700
Data Index: 5739187 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2688. Min Act: -0.1700
Data Index: 28660 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2531. Min Act: -0.1700
Data Index: 46731 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2374. Min Act: -0.1700
Data Index: 4645254 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2374. Min Act: -0.1700
Data Index: 3732151 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2059. Min Act: -0.1700
Data Index: 6008512 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2059. Min Act: -0.1700
Data Index: 4703341 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2059. Min Act: -0.1700
Data Index: 8608916 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2059. Min Act: -0.1700
Data Index: 5643874 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2217. Min Act: -0.1700
Data Index: 8148075 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.1902. Min Act: -0.1700
Data Index: 8148074 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.2059. Min Act: -0.1700
Data Index: 3951957 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.1902. Min Act: -0.1700
Data Index: 647128 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6606. Min Range: -3.6606
Max Act: 3.1587. Min Act: -0.1700
Data Index: 7237762 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19