Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0441. Min Range: -9.0441
Max Act: 9.0441. Min Act: -0.1700
Data Index: 4386365 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.6066. Min Act: -0.1700
Data Index: 1785706 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.6066. Min Act: -0.1700
Data Index: 4898918 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.6066. Min Act: -0.1700
Data Index: 6410915 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.6066. Min Act: -0.1700
Data Index: 8535360 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.4816. Min Act: -0.1700
Data Index: 3465913 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.4816. Min Act: -0.1700
Data Index: 175213 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.4816. Min Act: -0.1700
Data Index: 6610745 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.4191. Min Act: -0.1700
Data Index: 5318791 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.3566. Min Act: -0.1700
Data Index: 5606890 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.2941. Min Act: -0.1700
Data Index: 4757110 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.2941. Min Act: -0.1700
Data Index: 6965081 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.2316. Min Act: -0.1700
Data Index: 6887267 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.2316. Min Act: -0.1700
Data Index: 1254985 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.2941. Min Act: -0.1700
Data Index: 8764662 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.2316. Min Act: -0.1700
Data Index: 2912887 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.1691. Min Act: -0.1700
Data Index: 5236884 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.1691. Min Act: -0.1700
Data Index: 8176863 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.1691. Min Act: -0.1700
Data Index: 515039 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0441. Min Range: -9.0441
Max Act: 8.1691. Min Act: -0.1700
Data Index: 1332238 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19