Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7003. Min Range: -6.7003
Max Act: 6.7003. Min Act: -0.1700
Data Index: 1801012 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7003. Min Range: -6.7003
Max Act: 6.7003. Min Act: -0.1700
Data Index: 4154670 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7003. Min Range: -6.7003
Max Act: 6.5128. Min Act: -0.1700
Data Index: 3879546 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7003. Min Range: -6.7003
Max Act: 6.2316. Min Act: -0.1700
Data Index: 167453 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7003. Min Range: -6.7003
Max Act: 6.1378. Min Act: -0.1700
Data Index: 4506420 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7003. Min Range: -6.7003
Max Act: 6.0753. Min Act: -0.1700
Data Index: 1048420 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7003. Min Range: -6.7003
Max Act: 6.0753. Min Act: -0.1700
Data Index: 6981753 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7003. Min Range: -6.7003
Max Act: 6.0753. Min Act: -0.1700
Data Index: 2726495 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7003. Min Range: -6.7003
Max Act: 6.0128. Min Act: -0.1700
Data Index: 4939269 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.9816. Min Act: -0.1700
Data Index: 4123831 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.9816. Min Act: -0.1700
Data Index: 7830791 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.9816. Min Act: -0.1700
Data Index: 2272858 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.9191. Min Act: -0.1700
Data Index: 4716956 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.9503. Min Act: -0.1700
Data Index: 7761118 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.9191. Min Act: -0.1700
Data Index: 2014699 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.8878. Min Act: -0.1700
Data Index: 1055264 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.8566. Min Act: -0.1700
Data Index: 7674438 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.8566. Min Act: -0.1700
Data Index: 6629348 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.8566. Min Act: -0.1700
Data Index: 5071245 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7003. Min Range: -6.7003
Max Act: 5.8253. Min Act: -0.1700
Data Index: 6935703 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19