Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0891. Min Range: -4.0891
Max Act: 4.0891. Min Act: -0.1700
Data Index: 3901695 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9016. Min Act: -0.1700
Data Index: 3429445 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.6983. Min Act: -0.1700
Data Index: 6348527 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.6670. Min Act: -0.1700
Data Index: 8334701 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.6357. Min Act: -0.1700
Data Index: 6609497 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.6201. Min Act: -0.1700
Data Index: 7126449 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.6044. Min Act: -0.1700
Data Index: 2218666 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.5575. Min Act: -0.1700
Data Index: 8496384 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.5575. Min Act: -0.1700
Data Index: 7210869 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.5418. Min Act: -0.1700
Data Index: 6693794 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.5418. Min Act: -0.1700
Data Index: 2781816 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.5261. Min Act: -0.1700
Data Index: 7389448 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.5261. Min Act: -0.1700
Data Index: 6630992 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.5105. Min Act: -0.1700
Data Index: 1391570 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.4948. Min Act: -0.1700
Data Index: 5557508 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.5105. Min Act: -0.1700
Data Index: 7446382 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.4948. Min Act: -0.1700
Data Index: 6090130 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.4791. Min Act: -0.1700
Data Index: 8210074 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.4791. Min Act: -0.1700
Data Index: 8269452 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.4791. Min Act: -0.1700
Data Index: 83760 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19