Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2230 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1843. Min Range: -6.1843
Max Act: 6.1843. Min Act: -0.1700
Data Index: 3764442 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1843. Min Range: -6.1843
Max Act: 6.0593. Min Act: -0.1700
Data Index: 4059016 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1843. Min Range: -6.1843
Max Act: 6.0593. Min Act: -0.1700
Data Index: 4010046 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.9968. Min Act: -0.1700
Data Index: 2944427 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.8718. Min Act: -0.1700
Data Index: 3139057 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.8093. Min Act: -0.1700
Data Index: 689628 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.7468. Min Act: -0.1700
Data Index: 5911233 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.7468. Min Act: -0.1700
Data Index: 2425754 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.6843. Min Act: -0.1700
Data Index: 2016937 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.6530. Min Act: -0.1700
Data Index: 4839904 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.6218. Min Act: -0.1700
Data Index: 3730901 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.6218. Min Act: -0.1700
Data Index: 3321144 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.6530. Min Act: -0.1700
Data Index: 7509347 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.5905. Min Act: -0.1700
Data Index: 3024319 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.5905. Min Act: -0.1700
Data Index: 3941122 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.5905. Min Act: -0.1700
Data Index: 8546104 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.5905. Min Act: -0.1700
Data Index: 3237830 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.5905. Min Act: -0.1700
Data Index: 5617969 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.5593. Min Act: -0.1700
Data Index: 2554773 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1843. Min Range: -6.1843
Max Act: 5.5593. Min Act: -0.1700
Data Index: 5900136 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19