Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0564. Min Range: -4.0564
Max Act: 4.0564. Min Act: -0.1700
Data Index: 8011541 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.9938. Min Act: -0.1700
Data Index: 2552006 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.9626. Min Act: -0.1700
Data Index: 8635868 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.9313. Min Act: -0.1700
Data Index: 813243 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.9000. Min Act: -0.1700
Data Index: 882372 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.8688. Min Act: -0.1700
Data Index: 5997484 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.8688. Min Act: -0.1700
Data Index: 3829744 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.8688. Min Act: -0.1700
Data Index: 846193 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.8375. Min Act: -0.1700
Data Index: 8727952 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.8062. Min Act: -0.1700
Data Index: 4450264 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7750. Min Act: -0.1700
Data Index: 6970658 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7593. Min Act: -0.1700
Data Index: 7538855 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7593. Min Act: -0.1700
Data Index: 3337632 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7437. Min Act: -0.1700
Data Index: 5925670 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7437. Min Act: -0.1700
Data Index: 1826285 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7280. Min Act: -0.1700
Data Index: 6465245 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7280. Min Act: -0.1700
Data Index: 3980014 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7124. Min Act: -0.1700
Data Index: 218682 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7124. Min Act: -0.1700
Data Index: 2043950 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0564. Min Range: -4.0564
Max Act: 3.7280. Min Act: -0.1700
Data Index: 1169619 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19