Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.4727. Min Act: -0.1700
Data Index: 5011817 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.2539. Min Act: -0.1700
Data Index: 3431977 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.2227. Min Act: -0.1700
Data Index: 6093948 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.1602. Min Act: -0.1700
Data Index: 6888315 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.1914. Min Act: -0.1700
Data Index: 7397490 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.1602. Min Act: -0.1700
Data Index: 8312936 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.1289. Min Act: -0.1700
Data Index: 199532 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.1289. Min Act: -0.1700
Data Index: 680714 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.0977. Min Act: -0.1700
Data Index: 609322 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.0664. Min Act: -0.1700
Data Index: 3320670 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.0977. Min Act: -0.1700
Data Index: 834832 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.0664. Min Act: -0.1700
Data Index: 8235937 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.0352. Min Act: -0.1700
Data Index: 2066463 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4727. Min Range: -7.4727
Max Act: 6.9727. Min Act: -0.1700
Data Index: 3252464 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4727. Min Range: -7.4727
Max Act: 6.9727. Min Act: -0.1700
Data Index: 81174 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4727. Min Range: -7.4727
Max Act: 6.9727. Min Act: -0.1700
Data Index: 4175899 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4727. Min Range: -7.4727
Max Act: 6.9727. Min Act: -0.1700
Data Index: 808062 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4727. Min Range: -7.4727
Max Act: 6.9727. Min Act: -0.1700
Data Index: 3707269 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.0039. Min Act: -0.1700
Data Index: 5987969 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4727. Min Range: -7.4727
Max Act: 7.0039. Min Act: -0.1700
Data Index: 5396201 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19