Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 686 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.4502. Min Act: -0.1700
Data Index: 2902904 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.4502. Min Act: -0.1700
Data Index: 2869400 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.3877. Min Act: -0.1700
Data Index: 795062 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.2940. Min Act: -0.1700
Data Index: 5972452 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.2940. Min Act: -0.1700
Data Index: 4585434 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.1690. Min Act: -0.1700
Data Index: 5017032 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.1377. Min Act: -0.1700
Data Index: 4566957 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.1377. Min Act: -0.1700
Data Index: 117543 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.1377. Min Act: -0.1700
Data Index: 4551115 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.1065. Min Act: -0.1700
Data Index: 641261 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.1065. Min Act: -0.1700
Data Index: 6506954 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.0440. Min Act: -0.1700
Data Index: 6026872 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.0440. Min Act: -0.1700
Data Index: 1530388 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.0127. Min Act: -0.1700
Data Index: 6077719 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.0440. Min Act: -0.1700
Data Index: 2049274 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.0440. Min Act: -0.1700
Data Index: 1251194 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.0440. Min Act: -0.1700
Data Index: 3386552 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.0127. Min Act: -0.1700
Data Index: 6317099 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.0440. Min Act: -0.1700
Data Index: 3252377 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4502. Min Range: -7.4502
Max Act: 7.0127. Min Act: -0.1700
Data Index: 492955 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19