Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4038 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.8580. Min Act: -0.1700
Data Index: 8158571 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.8267. Min Act: -0.1700
Data Index: 300401 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.8267. Min Act: -0.1700
Data Index: 2251226 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.7172. Min Act: -0.1700
Data Index: 5910017 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.7172. Min Act: -0.1700
Data Index: 5277396 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.6860. Min Act: -0.1700
Data Index: 5833201 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.7172. Min Act: -0.1700
Data Index: 1777779 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.6547. Min Act: -0.1700
Data Index: 5854580 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.6547. Min Act: -0.1700
Data Index: 8031161 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.6390. Min Act: -0.1700
Data Index: 1799601 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.5921. Min Act: -0.1700
Data Index: 4895737 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.5764. Min Act: -0.1700
Data Index: 1241008 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.5921. Min Act: -0.1700
Data Index: 7685884 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.6077. Min Act: -0.1700
Data Index: 8320700 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.5608. Min Act: -0.1700
Data Index: 8006536 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.6077. Min Act: -0.1700
Data Index: 2489300 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.5764. Min Act: -0.1700
Data Index: 2661492 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.5451. Min Act: -0.1700
Data Index: 1401008 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.5608. Min Act: -0.1700
Data Index: 5680578 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8580. Min Range: -3.8580
Max Act: 3.5451. Min Act: -0.1700
Data Index: 6775115 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19