Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 800 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.4584. Min Act: -0.1700
Data Index: 3122062 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.2387. Min Act: -0.1700
Data Index: 314368 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.2230. Min Act: -0.1700
Data Index: 4935788 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.2073. Min Act: -0.1700
Data Index: 530379 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1759. Min Act: -0.1700
Data Index: 1116612 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1759. Min Act: -0.1700
Data Index: 200541 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1601. Min Act: -0.1700
Data Index: 8776853 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1286. Min Act: -0.1700
Data Index: 6845624 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1286. Min Act: -0.1700
Data Index: 6830606 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1129. Min Act: -0.1700
Data Index: 5408477 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1129. Min Act: -0.1700
Data Index: 1004301 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1129. Min Act: -0.1700
Data Index: 7644967 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1129. Min Act: -0.1700
Data Index: 188898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1129. Min Act: -0.1700
Data Index: 2268492 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1129. Min Act: -0.1700
Data Index: 4455861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1129. Min Act: -0.1700
Data Index: 343091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.1129. Min Act: -0.1700
Data Index: 4594855 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.0814. Min Act: -0.1700
Data Index: 7076532 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.0814. Min Act: -0.1700
Data Index: 3532499 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4584. Min Range: -3.4584
Max Act: 3.0498. Min Act: -0.1700
Data Index: 6877851 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19