Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5724 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0473. Min Range: -7.0473
Max Act: 7.0473. Min Act: -0.1700
Data Index: 8318911 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.7660. Min Act: -0.1700
Data Index: 5150626 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.6410. Min Act: -0.1700
Data Index: 5485169 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.5785. Min Act: -0.1700
Data Index: 3862740 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.5785. Min Act: -0.1700
Data Index: 2169771 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.5785. Min Act: -0.1700
Data Index: 1622729 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.4848. Min Act: -0.1700
Data Index: 8260724 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.4535. Min Act: -0.1700
Data Index: 4471943 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.4223. Min Act: -0.1700
Data Index: 7935125 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.3910. Min Act: -0.1700
Data Index: 3505147 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.3910. Min Act: -0.1700
Data Index: 4464727 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.3598. Min Act: -0.1700
Data Index: 397473 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.3285. Min Act: -0.1700
Data Index: 5826934 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.3285. Min Act: -0.1700
Data Index: 8531863 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.3285. Min Act: -0.1700
Data Index: 1871891 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.3285. Min Act: -0.1700
Data Index: 2811851 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.3285. Min Act: -0.1700
Data Index: 3088456 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.2973. Min Act: -0.1700
Data Index: 7230471 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.2660. Min Act: -0.1700
Data Index: 4728445 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0473. Min Range: -7.0473
Max Act: 6.2348. Min Act: -0.1700
Data Index: 2518212 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19