Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.2384. Min Act: -0.1700
Data Index: 685170 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 2433092 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 8425868 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 4760852 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 3420279 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 2637413 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 1381076 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 1781158 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 2264265 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 2027937 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2384. Min Range: -9.2384
Max Act: 8.9884. Min Act: -0.1700
Data Index: 7242927 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2384. Min Range: -9.2384
Max Act: 8.9884. Min Act: -0.1700
Data Index: 6386076 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2384. Min Range: -9.2384
Max Act: 8.9884. Min Act: -0.1700
Data Index: 4682659 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 7468289 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2384. Min Range: -9.2384
Max Act: 8.9884. Min Act: -0.1700
Data Index: 347709 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2384. Min Range: -9.2384
Max Act: 8.9884. Min Act: -0.1700
Data Index: 454797 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2384. Min Range: -9.2384
Max Act: 9.0509. Min Act: -0.1700
Data Index: 7553660 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2384. Min Range: -9.2384
Max Act: 8.9884. Min Act: -0.1700
Data Index: 110993 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2384. Min Range: -9.2384
Max Act: 8.9259. Min Act: -0.1700
Data Index: 5068279 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2384. Min Range: -9.2384
Max Act: 8.9884. Min Act: -0.1700
Data Index: 3689074 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19