Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1513 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0725. Min Range: -7.0725
Max Act: 7.0725. Min Act: -0.1700
Data Index: 4656653 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.7287. Min Act: -0.1700
Data Index: 6142685 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.7287. Min Act: -0.1700
Data Index: 7127993 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.7287. Min Act: -0.1700
Data Index: 2942387 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5412. Min Act: -0.1700
Data Index: 5169178 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.5100. Min Act: -0.1700
Data Index: 1871709 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.4475. Min Act: -0.1700
Data Index: 5680735 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.4475. Min Act: -0.1700
Data Index: 2017722 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.3537. Min Act: -0.1700
Data Index: 3023623 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.3850. Min Act: -0.1700
Data Index: 4285929 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.3225. Min Act: -0.1700
Data Index: 742015 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.2912. Min Act: -0.1700
Data Index: 1745271 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.2912. Min Act: -0.1700
Data Index: 996241 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.2912. Min Act: -0.1700
Data Index: 5798465 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.2912. Min Act: -0.1700
Data Index: 2474631 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.2600. Min Act: -0.1700
Data Index: 474726 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.2600. Min Act: -0.1700
Data Index: 5128815 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.2600. Min Act: -0.1700
Data Index: 6052505 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.2287. Min Act: -0.1700
Data Index: 4527218 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0725. Min Range: -7.0725
Max Act: 6.1975. Min Act: -0.1700
Data Index: 3406267 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19