Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.9638. Min Act: -0.1700
Data Index: 4487220 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.9638. Min Act: -0.1700
Data Index: 5220885 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.9325. Min Act: -0.1700
Data Index: 7693248 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.9325. Min Act: -0.1700
Data Index: 1565680 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.9013. Min Act: -0.1700
Data Index: 2900084 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8700. Min Act: -0.1700
Data Index: 1393058 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8700. Min Act: -0.1700
Data Index: 757425 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8700. Min Act: -0.1700
Data Index: 4603831 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8700. Min Act: -0.1700
Data Index: 7144254 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8700. Min Act: -0.1700
Data Index: 1565681 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8075. Min Act: -0.1700
Data Index: 2900096 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8388. Min Act: -0.1700
Data Index: 4066253 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8075. Min Act: -0.1700
Data Index: 5220887 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8075. Min Act: -0.1700
Data Index: 5220874 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8388. Min Act: -0.1700
Data Index: 6369138 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8388. Min Act: -0.1700
Data Index: 3389767 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8075. Min Act: -0.1700
Data Index: 6139886 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8075. Min Act: -0.1700
Data Index: 2845701 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.7763. Min Act: -0.1700
Data Index: 2379128 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9638. Min Range: -5.9638
Max Act: 5.8075. Min Act: -0.1700
Data Index: 2900079 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19