Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6808. Min Range: -8.6808
Max Act: 8.6808. Min Act: -0.1700
Data Index: 7845258 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6808. Min Range: -8.6808
Max Act: 8.1808. Min Act: -0.1700
Data Index: 2834659 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6808. Min Range: -8.6808
Max Act: 8.1808. Min Act: -0.1700
Data Index: 5425600 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6808. Min Range: -8.6808
Max Act: 8.1183. Min Act: -0.1700
Data Index: 6463194 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6808. Min Range: -8.6808
Max Act: 8.0870. Min Act: -0.1700
Data Index: 6546849 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6808. Min Range: -8.6808
Max Act: 8.0558. Min Act: -0.1700
Data Index: 4802806 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6808. Min Range: -8.6808
Max Act: 8.0245. Min Act: -0.1700
Data Index: 6499837 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.9308. Min Act: -0.1700
Data Index: 7975977 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.9308. Min Act: -0.1700
Data Index: 81619 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.8683. Min Act: -0.1700
Data Index: 4812891 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.8370. Min Act: -0.1700
Data Index: 8143493 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.8370. Min Act: -0.1700
Data Index: 5111837 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.8370. Min Act: -0.1700
Data Index: 6922234 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.8058. Min Act: -0.1700
Data Index: 6883204 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.7745. Min Act: -0.1700
Data Index: 745577 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.8058. Min Act: -0.1700
Data Index: 7612821 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.7433. Min Act: -0.1700
Data Index: 3272564 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.7745. Min Act: -0.1700
Data Index: 5715251 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.7433. Min Act: -0.1700
Data Index: 1462603 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6808. Min Range: -8.6808
Max Act: 7.7433. Min Act: -0.1700
Data Index: 1149832 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19