Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2379 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3309. Min Range: -10.3309
Max Act: 10.3309. Min Act: -0.1700
Data Index: 865060 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3309. Min Range: -10.3309
Max Act: 10.2684. Min Act: -0.1700
Data Index: 5405855 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3309. Min Range: -10.3309
Max Act: 10.1434. Min Act: -0.1700
Data Index: 1477134 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3309. Min Range: -10.3309
Max Act: 10.0809. Min Act: -0.1700
Data Index: 7075052 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3309. Min Range: -10.3309
Max Act: 10.0809. Min Act: -0.1700
Data Index: 7033134 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3309. Min Range: -10.3309
Max Act: 10.0809. Min Act: -0.1700
Data Index: 5747628 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3309. Min Range: -10.3309
Max Act: 10.0184. Min Act: -0.1700
Data Index: 2961628 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3309. Min Range: -10.3309
Max Act: 10.0184. Min Act: -0.1700
Data Index: 2021258 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3309. Min Range: -10.3309
Max Act: 10.0809. Min Act: -0.1689
Data Index: 4040463 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.8934. Min Act: -0.1700
Data Index: 2235870 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.8309. Min Act: -0.1700
Data Index: 3644145 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.8309. Min Act: -0.1700
Data Index: 7854457 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.8309. Min Act: -0.1700
Data Index: 4238773 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.8309. Min Act: -0.1700
Data Index: 6624933 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.7684. Min Act: -0.1699
Data Index: 435775 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.7684. Min Act: -0.1700
Data Index: 2269857 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.7059. Min Act: -0.1698
Data Index: 4347763 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.7684. Min Act: -0.1700
Data Index: 5885025 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.7059. Min Act: -0.1700
Data Index: 7942214 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3309. Min Range: -10.3309
Max Act: 9.7684. Min Act: -0.1700
Data Index: 2763319 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19