Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1885 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.9687. Min Act: -0.1700
Data Index: 4499549 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.9370. Min Act: -0.1700
Data Index: 7058429 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.9054. Min Act: -0.1700
Data Index: 4499547 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8895. Min Act: -0.1700
Data Index: 4499548 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8736. Min Act: -0.1700
Data Index: 4499550 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8577. Min Act: -0.1700
Data Index: 8279329 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8577. Min Act: -0.1700
Data Index: 726990 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8419. Min Act: -0.1700
Data Index: 601097 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8260. Min Act: -0.1700
Data Index: 7755214 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8577. Min Act: -0.1700
Data Index: 344417 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8100. Min Act: -0.1700
Data Index: 5448503 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8260. Min Act: -0.1700
Data Index: 7058428 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8100. Min Act: -0.1700
Data Index: 5703870 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.8100. Min Act: -0.1700
Data Index: 6659143 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.7941. Min Act: -0.1700
Data Index: 7785981 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.7941. Min Act: -0.1700
Data Index: 2559337 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.7622. Min Act: -0.1700
Data Index: 6659144 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.7622. Min Act: -0.1700
Data Index: 6659142 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.7463. Min Act: -0.1700
Data Index: 3323789 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9687. Min Range: -2.9687
Max Act: 2.7463. Min Act: -0.1700
Data Index: 3577048 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19