Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4326 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0509. Min Act: -0.0137
Data Index: 8387273 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0509. Min Act: -0.1487
Data Index: 4569651 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0351. Min Act: -0.1622
Data Index: 7719889 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0193. Min Act: -0.1294
Data Index: 7388007 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0193. Min Act: 0.5478
Data Index: 2095669 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0035. Min Act: 0.6192
Data Index: 736724 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0035. Min Act: 0.0522
Data Index: 6225806 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0035. Min Act: 0.4031
Data Index: 4365691 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0035. Min Act: -0.0814
Data Index: 7680845 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0509. Min Range: -3.0509
Max Act: 3.0035. Min Act: -0.0437
Data Index: 1790862 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9877. Min Act: -0.1220
Data Index: 2178906 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9877. Min Act: 0.2131
Data Index: 6081287 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9877. Min Act: 0.0801
Data Index: 7545273 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9719. Min Act: -0.1052
Data Index: 5061804 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9719. Min Act: -0.0716
Data Index: 6420362 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9719. Min Act: -0.1161
Data Index: 2438747 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9719. Min Act: 0.0706
Data Index: 65150 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9561. Min Act: -0.1312
Data Index: 1237058 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9561. Min Act: 0.3673
Data Index: 65149 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0509. Min Range: -3.0509
Max Act: 2.9561. Min Act: -0.1449
Data Index: 2467701 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19