Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.5383. Min Act: -0.1700
Data Index: 1592496 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.5696. Min Act: -0.1700
Data Index: 8355617 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.3508. Min Act: -0.1700
Data Index: 2531914 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.2883. Min Act: -0.1700
Data Index: 4139240 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.2571. Min Act: -0.1700
Data Index: 4381543 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.1633. Min Act: -0.1700
Data Index: 3522549 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.1633. Min Act: -0.1700
Data Index: 1812063 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.1633. Min Act: -0.1700
Data Index: 3712044 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.1321. Min Act: -0.1700
Data Index: 2043030 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.1321. Min Act: -0.1700
Data Index: 5830791 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.1321. Min Act: -0.1700
Data Index: 281676 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.1008. Min Act: -0.1700
Data Index: 2896688 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.0696. Min Act: -0.1700
Data Index: 199031 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.0696. Min Act: -0.1700
Data Index: 7348211 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.0696. Min Act: -0.1700
Data Index: 2701294 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.0071. Min Act: -0.1700
Data Index: 7271450 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.0071. Min Act: -0.1700
Data Index: 8593295 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5696. Min Range: -6.5696
Max Act: 5.9758. Min Act: -0.1700
Data Index: 3209228 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.0071. Min Act: -0.1700
Data Index: 942401 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5696. Min Range: -6.5696
Max Act: 6.0071. Min Act: -0.1700
Data Index: 7919791 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19