Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.6497. Min Act: -0.1700
Data Index: 6600677 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.3372. Min Act: -0.1700
Data Index: 7112373 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.3372. Min Act: -0.1700
Data Index: 2761900 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.2747. Min Act: -0.1700
Data Index: 8178101 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.2122. Min Act: -0.1700
Data Index: 2398332 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.1497. Min Act: -0.1700
Data Index: 6874214 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.1497. Min Act: -0.1700
Data Index: 5224845 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.0872. Min Act: -0.1700
Data Index: 8202179 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.0247. Min Act: -0.1700
Data Index: 3426678 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6497. Min Range: -8.6497
Max Act: 8.0247. Min Act: -0.1700
Data Index: 8190081 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.9622. Min Act: -0.1700
Data Index: 5570738 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.9622. Min Act: -0.1700
Data Index: 1609676 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.9622. Min Act: -0.1700
Data Index: 4577734 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.9622. Min Act: -0.1700
Data Index: 1827813 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.8997. Min Act: -0.1700
Data Index: 7117200 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.8997. Min Act: -0.1700
Data Index: 2264703 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.8997. Min Act: -0.1700
Data Index: 8205213 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.8997. Min Act: -0.1700
Data Index: 5284368 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.8997. Min Act: -0.1700
Data Index: 2475907 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6497. Min Range: -8.6497
Max Act: 7.8372. Min Act: -0.1700
Data Index: 7241687 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19