Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1528 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0378. Min Range: -4.0378
Max Act: 4.0378. Min Act: -0.1700
Data Index: 7567621 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.8502. Min Act: -0.1700
Data Index: 8117359 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.8189. Min Act: -0.1700
Data Index: 8038931 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.8502. Min Act: -0.1700
Data Index: 1151982 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.8502. Min Act: -0.1700
Data Index: 468234 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.8815. Min Act: -0.1700
Data Index: 337401 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.7877. Min Act: -0.1700
Data Index: 3277529 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.7564. Min Act: -0.1700
Data Index: 2736638 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.7564. Min Act: -0.1700
Data Index: 6840170 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.7251. Min Act: -0.1700
Data Index: 7719484 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.6938. Min Act: -0.1700
Data Index: 4701730 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.7251. Min Act: -0.1700
Data Index: 5894417 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.7251. Min Act: -0.1700
Data Index: 6293757 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.6938. Min Act: -0.1700
Data Index: 6813324 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.6938. Min Act: -0.1700
Data Index: 744607 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.6938. Min Act: -0.1700
Data Index: 5201049 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.6625. Min Act: -0.1700
Data Index: 440200 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.6625. Min Act: -0.1700
Data Index: 1844881 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.6625. Min Act: -0.1700
Data Index: 4415233 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0378. Min Range: -4.0378
Max Act: 3.6625. Min Act: -0.1700
Data Index: 4246311 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19