Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 946 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2434. Min Range: -5.2434
Max Act: 5.2434. Min Act: -0.1700
Data Index: 5957006 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2434. Min Range: -5.2434
Max Act: 5.1809. Min Act: -0.1700
Data Index: 7220550 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.9622. Min Act: -0.1700
Data Index: 4161981 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.9309. Min Act: -0.1700
Data Index: 4712182 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.9309. Min Act: -0.1700
Data Index: 387344 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.9309. Min Act: -0.1700
Data Index: 5908429 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.9309. Min Act: -0.1700
Data Index: 8348753 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.9309. Min Act: -0.1700
Data Index: 7452482 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8997. Min Act: -0.1700
Data Index: 5979907 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8684. Min Act: -0.1700
Data Index: 5957007 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8684. Min Act: -0.1700
Data Index: 4885853 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8684. Min Act: -0.1700
Data Index: 5672758 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8372. Min Act: -0.1700
Data Index: 5171269 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8059. Min Act: -0.1700
Data Index: 4389437 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8372. Min Act: -0.1700
Data Index: 7826330 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8372. Min Act: -0.1700
Data Index: 8620971 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8372. Min Act: -0.1700
Data Index: 2359030 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8372. Min Act: -0.1700
Data Index: 8310516 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8059. Min Act: -0.1700
Data Index: 7837064 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2434. Min Range: -5.2434
Max Act: 4.8059. Min Act: -0.1700
Data Index: 4986975 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19