Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0394. Min Range: -7.0394
Max Act: 7.0394. Min Act: -0.1700
Data Index: 6248653 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0394. Min Range: -7.0394
Max Act: 6.5706. Min Act: -0.1700
Data Index: 1462914 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0394. Min Range: -7.0394
Max Act: 6.2894. Min Act: -0.1700
Data Index: 8223264 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0394. Min Range: -7.0394
Max Act: 6.2581. Min Act: -0.1700
Data Index: 7565863 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0394. Min Range: -7.0394
Max Act: 6.2269. Min Act: -0.1700
Data Index: 560426 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0394. Min Range: -7.0394
Max Act: 6.1019. Min Act: -0.1700
Data Index: 7828218 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0394. Min Range: -7.0394
Max Act: 6.1019. Min Act: -0.1700
Data Index: 1324410 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0394. Min Range: -7.0394
Max Act: 6.0706. Min Act: -0.1700
Data Index: 8181957 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0394. Min Range: -7.0394
Max Act: 6.0394. Min Act: -0.1700
Data Index: 2394413 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.9769. Min Act: -0.1700
Data Index: 1976513 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.9456. Min Act: -0.1700
Data Index: 3889762 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.9144. Min Act: -0.1700
Data Index: 6654140 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.8519. Min Act: -0.1700
Data Index: 1015388 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.7581. Min Act: -0.1700
Data Index: 3262210 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.7581. Min Act: -0.1700
Data Index: 8155713 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.7269. Min Act: -0.1700
Data Index: 2835186 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.6956. Min Act: -0.1700
Data Index: 3918712 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.6644. Min Act: -0.1700
Data Index: 4296978 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.7269. Min Act: -0.1700
Data Index: 7479167 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0394. Min Range: -7.0394
Max Act: 5.6956. Min Act: -0.1700
Data Index: 1634300 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19