Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.6267. Min Act: -0.1700
Data Index: 1417009 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.4392. Min Act: -0.1700
Data Index: 5496758 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.4392. Min Act: -0.1700
Data Index: 456435 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.3454. Min Act: -0.1700
Data Index: 46977 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.3454. Min Act: -0.1700
Data Index: 2357238 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.2829. Min Act: -0.1700
Data Index: 4600951 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.2517. Min Act: -0.1700
Data Index: 7187180 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.2204. Min Act: -0.1700
Data Index: 2039250 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.2517. Min Act: -0.1700
Data Index: 3928069 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.2517. Min Act: -0.1700
Data Index: 8104314 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.2204. Min Act: -0.1700
Data Index: 445943 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.1267. Min Act: -0.1700
Data Index: 6849350 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.0954. Min Act: -0.1700
Data Index: 514240 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.0954. Min Act: -0.1700
Data Index: 6604468 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.0642. Min Act: -0.1700
Data Index: 8198845 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.0329. Min Act: -0.1700
Data Index: 1402022 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.0329. Min Act: -0.1700
Data Index: 3618042 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.0017. Min Act: -0.1700
Data Index: 7992330 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.0017. Min Act: -0.1700
Data Index: 8273038 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6267. Min Range: -7.6267
Max Act: 7.0017. Min Act: -0.1700
Data Index: 7091797 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19