Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.3732. Min Act: -0.1700
Data Index: 2739906 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.3107. Min Act: -0.1700
Data Index: 202976 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.2795. Min Act: -0.1700
Data Index: 376101 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.2482. Min Act: -0.1700
Data Index: 4791655 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.1857. Min Act: -0.1700
Data Index: 5144007 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.1857. Min Act: -0.1700
Data Index: 2170184 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0920. Min Act: -0.1700
Data Index: 336484 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0607. Min Act: -0.1700
Data Index: 7650610 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0920. Min Act: -0.1700
Data Index: 7512305 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0607. Min Act: -0.1700
Data Index: 431084 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0607. Min Act: -0.1700
Data Index: 4238003 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0607. Min Act: -0.1700
Data Index: 3040406 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0295. Min Act: -0.1700
Data Index: 7970988 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0295. Min Act: -0.1700
Data Index: 7805482 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0295. Min Act: -0.1700
Data Index: 7265376 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0295. Min Act: -0.1700
Data Index: 2657268 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0295. Min Act: -0.1700
Data Index: 5303263 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0295. Min Act: -0.1700
Data Index: 1928981 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0295. Min Act: -0.1700
Data Index: 5157106 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3732. Min Range: -5.3732
Max Act: 5.0295. Min Act: -0.1700
Data Index: 735573 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19