Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5577 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.8794. Min Act: -0.1700
Data Index: 6619958 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.8482. Min Act: -0.1700
Data Index: 2643688 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.8169. Min Act: -0.1700
Data Index: 5120834 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.8169. Min Act: -0.1700
Data Index: 1561837 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.7857. Min Act: -0.1700
Data Index: 923063 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.7544. Min Act: -0.1700
Data Index: 3512704 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.7232. Min Act: -0.1700
Data Index: 8334129 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.7544. Min Act: -0.1700
Data Index: 792076 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.7232. Min Act: -0.1700
Data Index: 2028346 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.7232. Min Act: -0.1700
Data Index: 7804386 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.7544. Min Act: -0.1700
Data Index: 6533694 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6919. Min Act: -0.1700
Data Index: 5993742 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6919. Min Act: -0.1700
Data Index: 4954472 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6294. Min Act: -0.1700
Data Index: 668899 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6606. Min Act: -0.1700
Data Index: 3872410 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6606. Min Act: -0.1700
Data Index: 6398596 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6606. Min Act: -0.1700
Data Index: 2017150 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6606. Min Act: -0.1700
Data Index: 748612 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6606. Min Act: -0.1700
Data Index: 8147153 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8794. Min Range: -4.8794
Max Act: 4.6606. Min Act: -0.1700
Data Index: 7889901 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19