Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1580 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.9653. Min Act: -0.1700
Data Index: 1203144 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.9337. Min Act: -0.1700
Data Index: 1815011 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.9337. Min Act: -0.1700
Data Index: 2581153 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.8861. Min Act: -0.1700
Data Index: 2834205 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.8861. Min Act: -0.1700
Data Index: 7285841 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.8702. Min Act: -0.1700
Data Index: 8673633 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.8544. Min Act: -0.1700
Data Index: 7981776 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.8066. Min Act: -0.1700
Data Index: 2804299 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7588. Min Act: -0.1700
Data Index: 8289826 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7588. Min Act: -0.1700
Data Index: 1815010 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7588. Min Act: -0.1700
Data Index: 4741183 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7588. Min Act: -0.1700
Data Index: 8289825 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7588. Min Act: -0.1700
Data Index: 6552116 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7429. Min Act: -0.1700
Data Index: 8095450 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7109. Min Act: -0.1700
Data Index: 436605 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7269. Min Act: -0.1700
Data Index: 5521105 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7269. Min Act: -0.1700
Data Index: 4521490 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.7269. Min Act: -0.1700
Data Index: 3630787 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.6949. Min Act: -0.1700
Data Index: 3918626 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9653. Min Range: -2.9653
Max Act: 2.6949. Min Act: -0.1700
Data Index: 5419680 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19