Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 92 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1250. Min Range: -8.1250
Max Act: 8.1250. Min Act: -0.1700
Data Index: 2233074 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1250. Min Range: -8.1250
Max Act: 8.0625. Min Act: -0.1700
Data Index: 5037615 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1250. Min Range: -8.1250
Max Act: 8.0000. Min Act: -0.1700
Data Index: 6901653 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1250. Min Range: -8.1250
Max Act: 8.0000. Min Act: -0.1700
Data Index: 87499 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.9375. Min Act: -0.1700
Data Index: 1517087 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.9375. Min Act: -0.1700
Data Index: 8632538 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.9375. Min Act: -0.1700
Data Index: 4791181 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.9375. Min Act: -0.1700
Data Index: 387570 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.9062. Min Act: -0.1700
Data Index: 4128371 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.8437. Min Act: -0.1700
Data Index: 4992534 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.8437. Min Act: -0.1700
Data Index: 3792413 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.8437. Min Act: -0.1700
Data Index: 4735546 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.8437. Min Act: -0.1700
Data Index: 6652781 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.8125. Min Act: -0.1700
Data Index: 4944874 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.8437. Min Act: -0.1700
Data Index: 7416426 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.8125. Min Act: -0.1700
Data Index: 1130247 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.8125. Min Act: -0.1700
Data Index: 1829524 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.7812. Min Act: -0.1700
Data Index: 5871075 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.7812. Min Act: -0.1700
Data Index: 313137 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1250. Min Range: -8.1250
Max Act: 7.7812. Min Act: -0.1700
Data Index: 6556151 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19