Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0465. Min Range: -8.0465
Max Act: 8.0465. Min Act: -0.1700
Data Index: 6311177 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.8590. Min Act: -0.1700
Data Index: 2272669 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.7340. Min Act: -0.1700
Data Index: 4190286 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.6403. Min Act: -0.1700
Data Index: 3265905 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.6403. Min Act: -0.1700
Data Index: 2813144 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.6403. Min Act: -0.1700
Data Index: 2788097 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.6403. Min Act: -0.1700
Data Index: 140698 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.6090. Min Act: -0.1700
Data Index: 7549478 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.6403. Min Act: -0.1700
Data Index: 3384505 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.6090. Min Act: -0.1700
Data Index: 4216352 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.5778. Min Act: -0.1700
Data Index: 4368150 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.5153. Min Act: -0.1700
Data Index: 2585469 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.5465. Min Act: -0.1700
Data Index: 1966176 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.5465. Min Act: -0.1700
Data Index: 526793 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.5465. Min Act: -0.1700
Data Index: 8827995 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.4528. Min Act: -0.1700
Data Index: 6018757 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.4840. Min Act: -0.1700
Data Index: 4035001 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.4528. Min Act: -0.1700
Data Index: 33676 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.4840. Min Act: -0.1700
Data Index: 3530442 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0465. Min Range: -8.0465
Max Act: 7.4840. Min Act: -0.1700
Data Index: 2029481 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19