Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5194 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.4872. Min Act: -0.1700
Data Index: 5164530 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.4247. Min Act: -0.1700
Data Index: 6069547 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.3934. Min Act: -0.1700
Data Index: 4098188 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.3934. Min Act: -0.1700
Data Index: 3307377 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.2684. Min Act: -0.1700
Data Index: 446272 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.2059. Min Act: -0.1700
Data Index: 4985064 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.2372. Min Act: -0.1700
Data Index: 5013045 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.2059. Min Act: -0.1700
Data Index: 1853020 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1747. Min Act: -0.1700
Data Index: 3705456 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1434. Min Act: -0.1700
Data Index: 5298852 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1747. Min Act: -0.1700
Data Index: 7714995 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1747. Min Act: -0.1700
Data Index: 5671024 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1747. Min Act: -0.1700
Data Index: 7168889 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1747. Min Act: -0.1700
Data Index: 3332392 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1434. Min Act: -0.1700
Data Index: 4696732 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1747. Min Act: -0.1700
Data Index: 5166523 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1434. Min Act: -0.1700
Data Index: 5646439 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1434. Min Act: -0.1700
Data Index: 3186218 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1434. Min Act: -0.1700
Data Index: 2970948 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4872. Min Range: -4.4872
Max Act: 4.1434. Min Act: -0.1700
Data Index: 2656783 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19