Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2062 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.8586. Min Act: -0.1700
Data Index: 8043766 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.5149. Min Act: -0.1700
Data Index: 5683676 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.2649. Min Act: -0.1700
Data Index: 5952519 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.1399. Min Act: -0.1700
Data Index: 4109134 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.1086. Min Act: -0.1700
Data Index: 1558652 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.1086. Min Act: -0.1700
Data Index: 1909877 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.0774. Min Act: -0.1700
Data Index: 8542837 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.0461. Min Act: -0.1700
Data Index: 4480638 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.0461. Min Act: -0.1700
Data Index: 5559560 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.0149. Min Act: -0.1700
Data Index: 2353080 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8586. Min Range: -7.8586
Max Act: 6.9836. Min Act: -0.1700
Data Index: 5395400 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8586. Min Range: -7.8586
Max Act: 7.0149. Min Act: -0.1700
Data Index: 766571 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8586. Min Range: -7.8586
Max Act: 6.9211. Min Act: -0.1700
Data Index: 8316617 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8586. Min Range: -7.8586
Max Act: 6.9524. Min Act: -0.1700
Data Index: 8686199 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8586. Min Range: -7.8586
Max Act: 6.9211. Min Act: -0.1700
Data Index: 8526507 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8586. Min Range: -7.8586
Max Act: 6.9524. Min Act: -0.1700
Data Index: 3277858 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8586. Min Range: -7.8586
Max Act: 6.9524. Min Act: -0.1700
Data Index: 8346764 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8586. Min Range: -7.8586
Max Act: 6.8586. Min Act: -0.1700
Data Index: 1075083 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8586. Min Range: -7.8586
Max Act: 6.8899. Min Act: -0.1700
Data Index: 2715670 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8586. Min Range: -7.8586
Max Act: 6.8899. Min Act: -0.1700
Data Index: 6404598 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19