Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.6331. Min Act: -0.1700
Data Index: 701612 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.4456. Min Act: -0.1696
Data Index: 4117371 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.1331. Min Act: -0.1698
Data Index: 3488371 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.0706. Min Act: -0.1700
Data Index: 6432370 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.0706. Min Act: -0.1700
Data Index: 850332 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6331. Min Range: -7.6331
Max Act: 7.0081. Min Act: -0.1700
Data Index: 480892 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.8831. Min Act: -0.1700
Data Index: 480887 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.7894. Min Act: -0.1598
Data Index: 4117358 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.6644. Min Act: -0.1699
Data Index: 2569199 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.6019. Min Act: -0.1687
Data Index: 7791408 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.5706. Min Act: -0.1699
Data Index: 4117360 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.5706. Min Act: -0.1699
Data Index: 3488370 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.5706. Min Act: -0.1700
Data Index: 3239846 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.5706. Min Act: -0.1700
Data Index: 4548728 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.5706. Min Act: -0.1697
Data Index: 3841338 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.5081. Min Act: -0.1689
Data Index: 2517363 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.5081. Min Act: -0.1700
Data Index: 4117362 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.4769. Min Act: -0.1700
Data Index: 7155141 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.3831. Min Act: -0.1247
Data Index: 2026315 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6331. Min Range: -7.6331
Max Act: 6.3831. Min Act: -0.1700
Data Index: 2811930 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19