Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4440 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.9439. Min Act: -0.1700
Data Index: 4021305 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.9439. Min Act: -0.1700
Data Index: 2529493 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.9126. Min Act: -0.1700
Data Index: 2119744 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.7876. Min Act: -0.1700
Data Index: 744602 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.7876. Min Act: -0.1700
Data Index: 3004548 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.7251. Min Act: -0.1700
Data Index: 6672711 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.7564. Min Act: -0.1700
Data Index: 7079626 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6939. Min Act: -0.1700
Data Index: 721325 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6939. Min Act: -0.1700
Data Index: 5367674 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6626. Min Act: -0.1700
Data Index: 8577437 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6314. Min Act: -0.1700
Data Index: 3397039 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6314. Min Act: -0.1700
Data Index: 5772372 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6314. Min Act: -0.1700
Data Index: 1657941 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6314. Min Act: -0.1700
Data Index: 1974710 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6001. Min Act: -0.1700
Data Index: 217090 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6314. Min Act: -0.1700
Data Index: 8034842 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6001. Min Act: -0.1700
Data Index: 7878326 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.6001. Min Act: -0.1700
Data Index: 1616220 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.5689. Min Act: -0.1700
Data Index: 4256683 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9439. Min Range: -6.9439
Max Act: 6.5689. Min Act: -0.1700
Data Index: 1683564 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19