Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.1314. Min Act: -0.1700
Data Index: 1780088 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.1314. Min Act: -0.1700
Data Index: 5543278 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.1314. Min Act: -0.1700
Data Index: 601882 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.1314. Min Act: -0.1700
Data Index: 8399477 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0689. Min Act: -0.1700
Data Index: 8734370 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.1002. Min Act: -0.1700
Data Index: 984556 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.1002. Min Act: -0.1700
Data Index: 461794 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0689. Min Act: -0.1700
Data Index: 2484118 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0377. Min Act: -0.1700
Data Index: 6190387 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0377. Min Act: -0.1700
Data Index: 1146601 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0377. Min Act: -0.1700
Data Index: 4297719 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0064. Min Act: -0.1700
Data Index: 1382831 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0064. Min Act: -0.1700
Data Index: 4907430 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0064. Min Act: -0.1700
Data Index: 6651314 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0064. Min Act: -0.1700
Data Index: 7573480 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0064. Min Act: -0.1700
Data Index: 5572354 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1314. Min Range: -4.1314
Max Act: 3.9751. Min Act: -0.1700
Data Index: 2706454 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1314. Min Range: -4.1314
Max Act: 3.9751. Min Act: -0.1700
Data Index: 1227785 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1314. Min Range: -4.1314
Max Act: 3.9751. Min Act: -0.1700
Data Index: 2270819 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1314. Min Range: -4.1314
Max Act: 4.0064. Min Act: -0.1700
Data Index: 4962586 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19