Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3751 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.8767. Min Range: -15.8767
Max Act: 15.8767. Min Act: -0.1700
Data Index: 7503872 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.8767. Min Range: -15.8767
Max Act: 15.7517. Min Act: -0.1700
Data Index: 6903026 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.8767. Min Range: -15.8767
Max Act: 15.6267. Min Act: -0.1700
Data Index: 1157186 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.8767. Min Range: -15.8767
Max Act: 15.4392. Min Act: -0.1700
Data Index: 7620488 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.8767. Min Range: -15.8767
Max Act: 15.1892. Min Act: -0.1700
Data Index: 4429854 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.8767. Min Range: -15.8767
Max Act: 15.0642. Min Act: -0.1699
Data Index: 1046994 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.8767. Min Range: -15.8767
Max Act: 15.0642. Min Act: -0.1700
Data Index: 1663745 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.8767. Min Range: -15.8767
Max Act: 15.0017. Min Act: -0.1700
Data Index: 1229625 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.9392. Min Act: -0.1700
Data Index: 3334044 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.9392. Min Act: -0.1700
Data Index: 5923185 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.8767. Min Act: -0.1700
Data Index: 2563100 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.8142. Min Act: -0.1700
Data Index: 4463329 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.8142. Min Act: -0.1700
Data Index: 6245501 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.7517. Min Act: -0.1700
Data Index: 134470 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.8142. Min Act: -0.1700
Data Index: 5033339 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.7517. Min Act: -0.1700
Data Index: 6948456 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.7517. Min Act: -0.1700
Data Index: 611017 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.7517. Min Act: -0.1700
Data Index: 7933437 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.6892. Min Act: -0.1700
Data Index: 173924 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.8767. Min Range: -15.8767
Max Act: 14.6892. Min Act: -0.1700
Data Index: 3138145 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19