Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 523 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.8562. Min Act: -0.1700
Data Index: 4832359 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.5437. Min Act: -0.1700
Data Index: 1604603 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.4812. Min Act: -0.1700
Data Index: 6151148 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.3250. Min Act: -0.1700
Data Index: 4293481 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.3250. Min Act: -0.1700
Data Index: 5443083 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.3250. Min Act: -0.1700
Data Index: 6955501 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.2312. Min Act: -0.1700
Data Index: 3705096 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.2312. Min Act: -0.1700
Data Index: 7321736 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.2000. Min Act: -0.1700
Data Index: 2523815 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.1375. Min Act: -0.1700
Data Index: 7485381 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.1375. Min Act: -0.1700
Data Index: 1069023 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.1687. Min Act: -0.1700
Data Index: 4818208 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.1062. Min Act: -0.1700
Data Index: 3054650 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.1062. Min Act: -0.1700
Data Index: 5261920 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.1062. Min Act: -0.1700
Data Index: 8582606 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.1062. Min Act: -0.1700
Data Index: 1091833 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.1062. Min Act: -0.1700
Data Index: 7379996 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.0437. Min Act: -0.1700
Data Index: 8779560 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.0437. Min Act: -0.1700
Data Index: 1740017 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8562. Min Range: -6.8562
Max Act: 6.0437. Min Act: -0.1700
Data Index: 8687855 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19