Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.6495. Min Act: -0.1700
Data Index: 2963148 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.5870. Min Act: -0.1700
Data Index: 4516635 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.5558. Min Act: -0.1700
Data Index: 2328297 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.5558. Min Act: -0.1700
Data Index: 1996453 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.5558. Min Act: -0.1700
Data Index: 7008038 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.5558. Min Act: -0.1700
Data Index: 2854126 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.5245. Min Act: -0.1700
Data Index: 881111 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.4933. Min Act: -0.1700
Data Index: 6143894 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.4620. Min Act: -0.1700
Data Index: 3673326 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.4308. Min Act: -0.1700
Data Index: 5377449 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.4620. Min Act: -0.1700
Data Index: 80827 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.3995. Min Act: -0.1700
Data Index: 3309104 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.3995. Min Act: -0.1700
Data Index: 3901063 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.3995. Min Act: -0.1700
Data Index: 4446107 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.3995. Min Act: -0.1700
Data Index: 1886954 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.4308. Min Act: -0.1700
Data Index: 823782 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.3683. Min Act: -0.1700
Data Index: 2563705 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.3995. Min Act: -0.1700
Data Index: 2549948 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.3683. Min Act: -0.1700
Data Index: 5000652 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6495. Min Range: -6.6495
Max Act: 6.3370. Min Act: -0.1700
Data Index: 3900215 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19