Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.7454. Min Act: -0.1700
Data Index: 5508672 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.7454. Min Act: -0.1700
Data Index: 5136988 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.7454. Min Act: -0.1700
Data Index: 6658100 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.6516. Min Act: -0.1700
Data Index: 3623847 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.6204. Min Act: -0.1700
Data Index: 4905717 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.5579. Min Act: -0.1700
Data Index: 1559210 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.5266. Min Act: -0.1700
Data Index: 1139987 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.4954. Min Act: -0.1700
Data Index: 7058429 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.4641. Min Act: -0.1700
Data Index: 5275751 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.4641. Min Act: -0.1700
Data Index: 8363734 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.4329. Min Act: -0.1700
Data Index: 3500641 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.4329. Min Act: -0.1700
Data Index: 6904178 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.4329. Min Act: -0.1700
Data Index: 8802684 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.4329. Min Act: -0.1700
Data Index: 8169575 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.4016. Min Act: -0.1700
Data Index: 2201806 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.3704. Min Act: -0.1700
Data Index: 149463 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.3704. Min Act: -0.1700
Data Index: 440712 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.3704. Min Act: -0.1700
Data Index: 7121720 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.3704. Min Act: -0.1700
Data Index: 2726146 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7454. Min Range: -4.7454
Max Act: 4.3079. Min Act: -0.1700
Data Index: 2827059 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19