Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1635 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.4493. Min Act: -0.1700
Data Index: 352567 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.3243. Min Act: -0.1700
Data Index: 5546766 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.2305. Min Act: -0.1700
Data Index: 451375 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.0430. Min Act: -0.1700
Data Index: 2502459 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4493. Min Range: -6.4493
Max Act: 6.0118. Min Act: -0.1700
Data Index: 8394902 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.9805. Min Act: -0.1700
Data Index: 5022717 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.9493. Min Act: -0.1700
Data Index: 3984528 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.9180. Min Act: -0.1700
Data Index: 5989571 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.8243. Min Act: -0.1700
Data Index: 6657000 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7930. Min Act: -0.1700
Data Index: 2299775 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.8243. Min Act: -0.1700
Data Index: 3969876 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7930. Min Act: -0.1700
Data Index: 2587295 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7930. Min Act: -0.1700
Data Index: 6788072 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7930. Min Act: -0.1700
Data Index: 7327565 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7618. Min Act: -0.1700
Data Index: 5868856 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7930. Min Act: -0.1700
Data Index: 7192275 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7618. Min Act: -0.1700
Data Index: 2233147 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7618. Min Act: -0.1700
Data Index: 1161193 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7930. Min Act: -0.1700
Data Index: 1035810 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4493. Min Range: -6.4493
Max Act: 5.7930. Min Act: -0.1700
Data Index: 4010986 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19