Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3939 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.8863. Min Act: -0.1700
Data Index: 5698239 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.7926. Min Act: -0.1700
Data Index: 3548856 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.7926. Min Act: -0.1700
Data Index: 2849823 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.7613. Min Act: -0.1700
Data Index: 3448738 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.7301. Min Act: -0.1700
Data Index: 6287444 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6988. Min Act: -0.1700
Data Index: 6287445 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6988. Min Act: -0.1700
Data Index: 3417282 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6988. Min Act: -0.1700
Data Index: 1513468 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6988. Min Act: -0.1700
Data Index: 1228278 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6051. Min Act: -0.1700
Data Index: 1970374 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6363. Min Act: -0.1700
Data Index: 5236190 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6051. Min Act: -0.1700
Data Index: 1465364 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6051. Min Act: -0.1700
Data Index: 7751021 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6051. Min Act: -0.1700
Data Index: 95253 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6051. Min Act: -0.1700
Data Index: 6456177 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.6051. Min Act: -0.1700
Data Index: 4500935 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.5738. Min Act: -0.1700
Data Index: 3522057 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.5426. Min Act: -0.1700
Data Index: 4609757 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.5426. Min Act: -0.1700
Data Index: 4084446 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8863. Min Range: -5.8863
Max Act: 5.5426. Min Act: -0.1700
Data Index: 2360824 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19