Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3693. Min Range: -5.3693
Max Act: 5.3693. Min Act: -0.1700
Data Index: 6833325 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.8380. Min Act: -0.1700
Data Index: 6893996 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.6818. Min Act: -0.1700
Data Index: 5982803 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.6818. Min Act: -0.1700
Data Index: 1490299 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.6818. Min Act: -0.1700
Data Index: 5414841 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.6505. Min Act: -0.1700
Data Index: 7491642 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.6505. Min Act: -0.1700
Data Index: 6422960 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.6193. Min Act: -0.1700
Data Index: 4366415 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5880. Min Act: -0.1700
Data Index: 3499149 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5880. Min Act: -0.1700
Data Index: 3510090 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.6193. Min Act: -0.1700
Data Index: 1461406 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.6193. Min Act: -0.1700
Data Index: 8503976 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5880. Min Act: -0.1700
Data Index: 3282132 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5880. Min Act: -0.1700
Data Index: 7167931 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5568. Min Act: -0.1700
Data Index: 2329631 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5568. Min Act: -0.1700
Data Index: 637587 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5568. Min Act: -0.1700
Data Index: 2774901 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5255. Min Act: -0.1700
Data Index: 4298848 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5255. Min Act: -0.1700
Data Index: 1279289 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3693. Min Range: -5.3693
Max Act: 4.5255. Min Act: -0.1700
Data Index: 4731471 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19