Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4376 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.8877. Min Act: -0.1700
Data Index: 6734398 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.7002. Min Act: -0.1700
Data Index: 6027408 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.2627. Min Act: -0.1700
Data Index: 233215 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.2314. Min Act: -0.1700
Data Index: 4780318 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.2002. Min Act: -0.1700
Data Index: 5684870 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.2002. Min Act: -0.1700
Data Index: 4494628 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.1064. Min Act: -0.1700
Data Index: 6602186 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.1064. Min Act: -0.1700
Data Index: 404901 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.1064. Min Act: -0.1700
Data Index: 8539685 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.0752. Min Act: -0.1700
Data Index: 6546367 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.0439. Min Act: -0.1700
Data Index: 5272406 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.0439. Min Act: -0.1700
Data Index: 186424 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.0439. Min Act: -0.1700
Data Index: 1320200 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.0127. Min Act: -0.1700
Data Index: 6429175 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8877. Min Range: -6.8877
Max Act: 6.0127. Min Act: -0.1700
Data Index: 5315909 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8877. Min Range: -6.8877
Max Act: 5.9814. Min Act: -0.1700
Data Index: 1541327 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8877. Min Range: -6.8877
Max Act: 5.9814. Min Act: -0.1700
Data Index: 7127409 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8877. Min Range: -6.8877
Max Act: 5.9814. Min Act: -0.1700
Data Index: 220870 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8877. Min Range: -6.8877
Max Act: 5.9814. Min Act: -0.1700
Data Index: 3912025 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8877. Min Range: -6.8877
Max Act: 5.9502. Min Act: -0.1700
Data Index: 6546369 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19