Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1103 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.8767. Min Act: -0.1700
Data Index: 929155 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.8142. Min Act: -0.1700
Data Index: 5219511 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.6892. Min Act: -0.1700
Data Index: 8380825 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.5017. Min Act: -0.1700
Data Index: 6735702 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.3142. Min Act: -0.1700
Data Index: 6781024 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.2517. Min Act: -0.1700
Data Index: 5758027 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.1892. Min Act: -0.1700
Data Index: 7433787 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.1892. Min Act: -0.1700
Data Index: 34392 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.0017. Min Act: -0.1700
Data Index: 2638959 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8767. Min Range: -12.8767
Max Act: 12.0017. Min Act: -0.1700
Data Index: 4706548 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.9392. Min Act: -0.1700
Data Index: 5529493 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.9392. Min Act: -0.1700
Data Index: 6490630 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.9392. Min Act: -0.1700
Data Index: 4358811 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.8767. Min Act: -0.1700
Data Index: 7976890 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.8142. Min Act: -0.1700
Data Index: 3900177 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.8767. Min Act: -0.1700
Data Index: 7848580 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.8767. Min Act: -0.1700
Data Index: 5086130 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.8767. Min Act: -0.1700
Data Index: 765836 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.8767. Min Act: -0.1700
Data Index: 8528252 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8767. Min Range: -12.8767
Max Act: 11.8142. Min Act: -0.1700
Data Index: 2396599 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19