Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1762 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.9387. Min Act: -0.1700
Data Index: 8770450 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.9387. Min Act: -0.1700
Data Index: 3293971 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8762. Min Act: -0.1700
Data Index: 5308097 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.8137. Min Act: -0.1700
Data Index: 5910476 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7980. Min Act: -0.1700
Data Index: 6660055 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7824. Min Act: -0.1700
Data Index: 5548901 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7667. Min Act: -0.1700
Data Index: 3350970 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7824. Min Act: -0.1700
Data Index: 613469 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7824. Min Act: -0.1700
Data Index: 1577745 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7667. Min Act: -0.1700
Data Index: 2375718 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7667. Min Act: -0.1700
Data Index: 4430461 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7511. Min Act: -0.1700
Data Index: 2929543 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7824. Min Act: -0.1700
Data Index: 7101270 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7667. Min Act: -0.1700
Data Index: 4186412 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7198. Min Act: -0.1700
Data Index: 1428692 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7355. Min Act: -0.1700
Data Index: 5217242 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7198. Min Act: -0.1700
Data Index: 7286994 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7198. Min Act: -0.1700
Data Index: 6755067 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7198. Min Act: -0.1700
Data Index: 627152 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9387. Min Range: -3.9387
Max Act: 3.7042. Min Act: -0.1700
Data Index: 3734419 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19