Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0502. Min Range: -5.0502
Max Act: 5.0502. Min Act: -0.1700
Data Index: 5645301 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.9877. Min Act: -0.1700
Data Index: 1225563 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.9564. Min Act: -0.1700
Data Index: 3547422 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.9252. Min Act: -0.1700
Data Index: 4694348 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.8939. Min Act: -0.1700
Data Index: 8262627 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.8939. Min Act: -0.1700
Data Index: 5665279 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.8627. Min Act: -0.1700
Data Index: 4393371 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.8627. Min Act: -0.1700
Data Index: 6612212 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.8314. Min Act: -0.1700
Data Index: 3150045 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.8002. Min Act: -0.1700
Data Index: 1882408 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.8314. Min Act: -0.1700
Data Index: 4309759 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.8314. Min Act: -0.1700
Data Index: 39420 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.7689. Min Act: -0.1700
Data Index: 6816295 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.8002. Min Act: -0.1700
Data Index: 4789867 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.7689. Min Act: -0.1700
Data Index: 7429736 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.7689. Min Act: -0.1700
Data Index: 6275757 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.7377. Min Act: -0.1700
Data Index: 6572348 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.7064. Min Act: -0.1700
Data Index: 2335149 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.7377. Min Act: -0.1700
Data Index: 1991185 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0502. Min Range: -5.0502
Max Act: 4.7064. Min Act: -0.1700
Data Index: 2026876 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19