Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1159 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.7195. Min Act: -0.1700
Data Index: 4676213 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.5945. Min Act: -0.1700
Data Index: 5306107 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.4070. Min Act: -0.1700
Data Index: 1315271 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.4070. Min Act: -0.1700
Data Index: 8772582 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.2820. Min Act: -0.1700
Data Index: 4199002 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.2195. Min Act: -0.1700
Data Index: 1938186 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.2195. Min Act: -0.1700
Data Index: 4955282 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.2195. Min Act: -0.1700
Data Index: 5845276 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.0320. Min Act: -0.1700
Data Index: 8011330 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.0320. Min Act: -0.1700
Data Index: 1635610 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.0008. Min Act: -0.1700
Data Index: 7037611 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.0008. Min Act: -0.1700
Data Index: 5072351 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7195. Min Range: -8.7195
Max Act: 8.0008. Min Act: -0.1700
Data Index: 226744 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7195. Min Range: -8.7195
Max Act: 7.9383. Min Act: -0.1700
Data Index: 7854907 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7195. Min Range: -8.7195
Max Act: 7.9383. Min Act: -0.1700
Data Index: 5402129 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7195. Min Range: -8.7195
Max Act: 7.9383. Min Act: -0.1700
Data Index: 1096689 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7195. Min Range: -8.7195
Max Act: 7.9070. Min Act: -0.1700
Data Index: 2708953 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7195. Min Range: -8.7195
Max Act: 7.9070. Min Act: -0.1700
Data Index: 279029 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7195. Min Range: -8.7195
Max Act: 7.8758. Min Act: -0.1700
Data Index: 8363059 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7195. Min Range: -8.7195
Max Act: 7.9070. Min Act: -0.1700
Data Index: 1139962 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19