Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1724. Min Range: -8.1724
Max Act: 8.1724. Min Act: -0.1700
Data Index: 1433170 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1724. Min Range: -8.1724
Max Act: 8.1724. Min Act: -0.1700
Data Index: 30131 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1724. Min Range: -8.1724
Max Act: 8.1411. Min Act: -0.1700
Data Index: 6140341 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1724. Min Range: -8.1724
Max Act: 8.0786. Min Act: -0.1700
Data Index: 2783900 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1724. Min Range: -8.1724
Max Act: 8.0786. Min Act: -0.1700
Data Index: 2620668 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1724. Min Range: -8.1724
Max Act: 8.0786. Min Act: -0.1700
Data Index: 8422660 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1724. Min Range: -8.1724
Max Act: 8.1099. Min Act: -0.1700
Data Index: 3837047 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1724. Min Range: -8.1724
Max Act: 8.0161. Min Act: -0.1700
Data Index: 7383665 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.9536. Min Act: -0.1700
Data Index: 488945 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.9224. Min Act: -0.1700
Data Index: 5932710 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.8911. Min Act: -0.1700
Data Index: 8654102 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.8911. Min Act: -0.1700
Data Index: 983768 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.8599. Min Act: -0.1700
Data Index: 7466937 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.8911. Min Act: -0.1700
Data Index: 1811842 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.8911. Min Act: -0.1700
Data Index: 7212476 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.8286. Min Act: -0.1700
Data Index: 1887509 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.8599. Min Act: -0.1700
Data Index: 6852303 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.8286. Min Act: -0.1700
Data Index: 7402790 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.8286. Min Act: -0.1700
Data Index: 4507382 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1724. Min Range: -8.1724
Max Act: 7.7974. Min Act: -0.1700
Data Index: 7684774 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19