Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 968 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1392. Min Range: -5.1392
Max Act: 5.1392. Min Act: -0.1700
Data Index: 300824 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1392. Min Range: -5.1392
Max Act: 5.1080. Min Act: -0.1700
Data Index: 1042550 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1392. Min Range: -5.1392
Max Act: 5.0142. Min Act: -0.1700
Data Index: 4736474 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.9830. Min Act: -0.1700
Data Index: 6960405 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.9517. Min Act: -0.1700
Data Index: 941554 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.8267. Min Act: -0.1700
Data Index: 4267894 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.7955. Min Act: -0.1700
Data Index: 7258788 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.7955. Min Act: -0.1700
Data Index: 5869520 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.7955. Min Act: -0.1700
Data Index: 8567399 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.7642. Min Act: -0.1700
Data Index: 8596490 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.7330. Min Act: -0.1700
Data Index: 7936887 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.7330. Min Act: -0.1700
Data Index: 3005771 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.7017. Min Act: -0.1700
Data Index: 4467291 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.7017. Min Act: -0.1700
Data Index: 6938311 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.7017. Min Act: -0.1700
Data Index: 4267895 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.6705. Min Act: -0.1700
Data Index: 7557090 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.6705. Min Act: -0.1700
Data Index: 6910300 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.6392. Min Act: -0.1700
Data Index: 2222576 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.6392. Min Act: -0.1700
Data Index: 7272624 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1392. Min Range: -5.1392
Max Act: 4.6392. Min Act: -0.1700
Data Index: 6797211 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19