Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4390 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.6313. Min Act: -0.1700
Data Index: 1280837 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.3188. Min Act: -0.1700
Data Index: 8739409 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.3188. Min Act: -0.1700
Data Index: 8689636 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1938. Min Act: -0.1700
Data Index: 4320963 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.2250. Min Act: -0.1700
Data Index: 2036984 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.2250. Min Act: -0.1700
Data Index: 2480927 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1938. Min Act: -0.1700
Data Index: 5801838 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1938. Min Act: -0.1700
Data Index: 3386405 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1938. Min Act: -0.1700
Data Index: 2143110 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1938. Min Act: -0.1700
Data Index: 4317059 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1625. Min Act: -0.1700
Data Index: 7077114 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1625. Min Act: -0.1700
Data Index: 420275 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1313. Min Act: -0.1700
Data Index: 5773375 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1313. Min Act: -0.1700
Data Index: 5504764 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1000. Min Act: -0.1700
Data Index: 1422093 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1000. Min Act: -0.1700
Data Index: 7013492 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1313. Min Act: -0.1700
Data Index: 7783259 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.1000. Min Act: -0.1700
Data Index: 2112300 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.0688. Min Act: -0.1700
Data Index: 8689103 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6313. Min Range: -5.6313
Max Act: 5.0688. Min Act: -0.1700
Data Index: 1482036 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19