Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1403 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0828. Min Range: -7.0828
Max Act: 7.0828. Min Act: -0.1700
Data Index: 2064079 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0828. Min Range: -7.0828
Max Act: 7.0203. Min Act: -0.1700
Data Index: 1651226 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.8015. Min Act: -0.1700
Data Index: 1195161 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.7390. Min Act: -0.1700
Data Index: 6982414 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.6765. Min Act: -0.1700
Data Index: 3689848 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.6453. Min Act: -0.1700
Data Index: 7456646 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.6140. Min Act: -0.1700
Data Index: 342549 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.6140. Min Act: -0.1700
Data Index: 5104716 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.6140. Min Act: -0.1700
Data Index: 2372513 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.5515. Min Act: -0.1700
Data Index: 6926929 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.5515. Min Act: -0.1700
Data Index: 5695046 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.5203. Min Act: -0.1700
Data Index: 3281986 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.5203. Min Act: -0.1700
Data Index: 5732606 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.5203. Min Act: -0.1700
Data Index: 3066465 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.4890. Min Act: -0.1700
Data Index: 4219035 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.4890. Min Act: -0.1700
Data Index: 5738096 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.4578. Min Act: -0.1700
Data Index: 1969405 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.4890. Min Act: -0.1700
Data Index: 1259853 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.4890. Min Act: -0.1700
Data Index: 7927083 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0828. Min Range: -7.0828
Max Act: 6.4265. Min Act: -0.1700
Data Index: 7093255 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19