Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.3512. Min Act: -0.1700
Data Index: 2685277 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.1637. Min Act: -0.1700
Data Index: 7592545 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.1637. Min Act: -0.1700
Data Index: 4088832 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.1012. Min Act: -0.1700
Data Index: 7090503 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.0699. Min Act: -0.1700
Data Index: 1268554 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.0699. Min Act: -0.1700
Data Index: 8776792 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.0699. Min Act: -0.1700
Data Index: 8771709 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.0387. Min Act: -0.1700
Data Index: 3915634 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.0074. Min Act: -0.1700
Data Index: 6716966 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.0074. Min Act: -0.1700
Data Index: 4215040 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3512. Min Range: -5.3512
Max Act: 5.0387. Min Act: -0.1700
Data Index: 912178 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3512. Min Range: -5.3512
Max Act: 4.9762. Min Act: -0.1700
Data Index: 2036765 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3512. Min Range: -5.3512
Max Act: 4.9762. Min Act: -0.1700
Data Index: 7875660 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3512. Min Range: -5.3512
Max Act: 4.9762. Min Act: -0.1700
Data Index: 7764714 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3512. Min Range: -5.3512
Max Act: 4.9449. Min Act: -0.1700
Data Index: 2090514 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3512. Min Range: -5.3512
Max Act: 4.9137. Min Act: -0.1700
Data Index: 7673739 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3512. Min Range: -5.3512
Max Act: 4.8824. Min Act: -0.1700
Data Index: 7941520 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3512. Min Range: -5.3512
Max Act: 4.8512. Min Act: -0.1700
Data Index: 302712 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3512. Min Range: -5.3512
Max Act: 4.8199. Min Act: -0.1700
Data Index: 6926026 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3512. Min Range: -5.3512
Max Act: 4.8199. Min Act: -0.1700
Data Index: 5299941 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19