Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 973 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.7692. Min Act: -0.1700
Data Index: 5655342 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.7536. Min Act: -0.1700
Data Index: 5500076 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.7379. Min Act: -0.1700
Data Index: 5467058 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.6910. Min Act: -0.1700
Data Index: 7194726 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.6597. Min Act: -0.1700
Data Index: 8139963 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.6597. Min Act: -0.1700
Data Index: 5428665 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.6441. Min Act: -0.1700
Data Index: 8299288 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.6441. Min Act: -0.1700
Data Index: 6022880 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.6128. Min Act: -0.1700
Data Index: 3603567 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.6284. Min Act: -0.1700
Data Index: 6743578 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.6128. Min Act: -0.1700
Data Index: 7445438 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.5971. Min Act: -0.1700
Data Index: 75284 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.5971. Min Act: -0.1700
Data Index: 7541572 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.5815. Min Act: -0.1700
Data Index: 8579709 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.5658. Min Act: -0.1700
Data Index: 3376874 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.5658. Min Act: -0.1700
Data Index: 330160 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.5345. Min Act: -0.1700
Data Index: 1043058 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.5502. Min Act: -0.1700
Data Index: 4595402 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.5502. Min Act: -0.1700
Data Index: 5579309 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7692. Min Range: -3.7692
Max Act: 3.5188. Min Act: -0.1700
Data Index: 1365223 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19