Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1740 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2153. Min Range: -7.2153
Max Act: 7.2153. Min Act: -0.1700
Data Index: 4931854 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2153. Min Range: -7.2153
Max Act: 7.2153. Min Act: -0.1700
Data Index: 697607 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2153. Min Range: -7.2153
Max Act: 7.1216. Min Act: -0.1700
Data Index: 3385600 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2153. Min Range: -7.2153
Max Act: 7.0903. Min Act: -0.1700
Data Index: 1626112 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2153. Min Range: -7.2153
Max Act: 7.0278. Min Act: -0.1700
Data Index: 5029501 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2153. Min Range: -7.2153
Max Act: 7.0278. Min Act: -0.1700
Data Index: 8247726 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.8403. Min Act: -0.1700
Data Index: 4899380 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.8403. Min Act: -0.1700
Data Index: 1932087 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.8403. Min Act: -0.1700
Data Index: 8443014 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.8403. Min Act: -0.1700
Data Index: 4801258 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.8091. Min Act: -0.1700
Data Index: 4058082 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.8091. Min Act: -0.1700
Data Index: 2651221 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.7466. Min Act: -0.1700
Data Index: 595892 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.7153. Min Act: -0.1700
Data Index: 7840804 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.7466. Min Act: -0.1700
Data Index: 1437369 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.7153. Min Act: -0.1700
Data Index: 7013876 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.7153. Min Act: -0.1699
Data Index: 2216448 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6841. Min Act: -0.1700
Data Index: 122257 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6528. Min Act: -0.1700
Data Index: 3563151 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2153. Min Range: -7.2153
Max Act: 6.6528. Min Act: -0.1700
Data Index: 816586 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19