Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 452 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1571. Min Range: -6.1571
Max Act: 6.1571. Min Act: -0.1700
Data Index: 2517561 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1571. Min Range: -6.1571
Max Act: 6.1571. Min Act: -0.1700
Data Index: 8195671 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.7821. Min Act: -0.1700
Data Index: 4265338 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.7821. Min Act: -0.1700
Data Index: 3084261 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.6884. Min Act: -0.1700
Data Index: 4296182 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.6884. Min Act: -0.1700
Data Index: 5789919 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.6259. Min Act: -0.1700
Data Index: 5554181 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.5634. Min Act: -0.1700
Data Index: 6670916 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.5634. Min Act: -0.1700
Data Index: 7095725 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.5321. Min Act: -0.1700
Data Index: 3251511 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.5009. Min Act: -0.1700
Data Index: 767674 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.5009. Min Act: -0.1700
Data Index: 3580065 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.5009. Min Act: -0.1700
Data Index: 302808 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.4696. Min Act: -0.1700
Data Index: 1502896 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.4696. Min Act: -0.1700
Data Index: 8198379 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.4696. Min Act: -0.1700
Data Index: 7883552 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.4696. Min Act: -0.1700
Data Index: 3570075 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.4696. Min Act: -0.1700
Data Index: 7148919 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.5009. Min Act: -0.1700
Data Index: 5227087 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1571. Min Range: -6.1571
Max Act: 5.4071. Min Act: -0.1700
Data Index: 3947669 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19