Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.3568. Min Act: -0.1700
Data Index: 860640 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2940. Min Act: -0.1700
Data Index: 1254057 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2783. Min Act: -0.1700
Data Index: 68104 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2626. Min Act: -0.1700
Data Index: 68117 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2626. Min Act: -0.1700
Data Index: 2602601 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2626. Min Act: -0.1700
Data Index: 717886 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2469. Min Act: -0.1700
Data Index: 4588093 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2469. Min Act: -0.1700
Data Index: 570600 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2469. Min Act: -0.1700
Data Index: 302670 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2469. Min Act: -0.1700
Data Index: 3254073 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2469. Min Act: -0.1700
Data Index: 4327296 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2312. Min Act: -0.1700
Data Index: 68103 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2312. Min Act: -0.1700
Data Index: 6156063 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.2154. Min Act: -0.1700
Data Index: 6648752 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.1840. Min Act: -0.1700
Data Index: 2105193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.1997. Min Act: -0.1700
Data Index: 5554227 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.1997. Min Act: -0.1700
Data Index: 5797280 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.1840. Min Act: -0.1700
Data Index: 6161524 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.1997. Min Act: -0.1700
Data Index: 2841732 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3568. Min Range: -3.3568
Max Act: 3.1997. Min Act: -0.1700
Data Index: 3392655 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19