Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0115. Min Range: -5.0115
Max Act: 5.0115. Min Act: -0.1700
Data Index: 7079547 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.8240. Min Act: -0.1699
Data Index: 7234668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7928. Min Act: -0.1700
Data Index: 7511676 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7615. Min Act: -0.1700
Data Index: 744134 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7615. Min Act: -0.1700
Data Index: 7234667 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7615. Min Act: -0.1700
Data Index: 4829519 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7303. Min Act: -0.1700
Data Index: 752165 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7615. Min Act: -0.1700
Data Index: 3944024 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7303. Min Act: -0.1700
Data Index: 1539848 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7303. Min Act: -0.1700
Data Index: 8518885 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7303. Min Act: -0.1700
Data Index: 5771724 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7303. Min Act: -0.1700
Data Index: 6082333 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7303. Min Act: -0.1700
Data Index: 7727418 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.7303. Min Act: -0.1700
Data Index: 5006841 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.6990. Min Act: -0.1700
Data Index: 7511675 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.6990. Min Act: -0.1700
Data Index: 6316052 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.6990. Min Act: -0.1700
Data Index: 4829518 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.6678. Min Act: -0.1700
Data Index: 5163481 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.6678. Min Act: -0.1700
Data Index: 3320246 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0115. Min Range: -5.0115
Max Act: 4.6678. Min Act: -0.1700
Data Index: 1685028 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19