Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4750 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3448. Min Range: -6.3448
Max Act: 6.3448. Min Act: -0.1700
Data Index: 5922534 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3448. Min Range: -6.3448
Max Act: 6.2823. Min Act: -0.1700
Data Index: 6689044 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3448. Min Range: -6.3448
Max Act: 6.0948. Min Act: -0.1700
Data Index: 759931 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3448. Min Range: -6.3448
Max Act: 6.0635. Min Act: -0.1700
Data Index: 7358855 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.9385. Min Act: -0.1700
Data Index: 11335 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.9073. Min Act: -0.1700
Data Index: 422351 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.8448. Min Act: -0.1700
Data Index: 2324268 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.7823. Min Act: -0.1700
Data Index: 3879280 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.7823. Min Act: -0.1700
Data Index: 7973922 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.7198. Min Act: -0.1700
Data Index: 7211894 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.7198. Min Act: -0.1700
Data Index: 7612010 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.7198. Min Act: -0.1700
Data Index: 7789483 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.6885. Min Act: -0.1700
Data Index: 5511469 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.6885. Min Act: -0.1700
Data Index: 1133965 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.6260. Min Act: -0.1700
Data Index: 8309553 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.6885. Min Act: -0.1700
Data Index: 2214480 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.6573. Min Act: -0.1700
Data Index: 4803948 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.6573. Min Act: -0.1700
Data Index: 1285118 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.6573. Min Act: -0.1700
Data Index: 807905 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3448. Min Range: -6.3448
Max Act: 5.6260. Min Act: -0.1700
Data Index: 400838 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19