Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3725 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3544. Min Range: -4.3544
Max Act: 4.3544. Min Act: -0.1700
Data Index: 7386561 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3544. Min Range: -4.3544
Max Act: 4.2606. Min Act: -0.1700
Data Index: 2128168 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3544. Min Range: -4.3544
Max Act: 4.1669. Min Act: -0.1700
Data Index: 4108277 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3544. Min Range: -4.3544
Max Act: 4.1669. Min Act: -0.1700
Data Index: 3827396 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3544. Min Range: -4.3544
Max Act: 4.0418. Min Act: -0.1700
Data Index: 5727143 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3544. Min Range: -4.3544
Max Act: 4.0731. Min Act: -0.1700
Data Index: 649596 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3544. Min Range: -4.3544
Max Act: 4.0418. Min Act: -0.1700
Data Index: 7506537 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9793. Min Act: -0.1700
Data Index: 8363328 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9793. Min Act: -0.1700
Data Index: 2687390 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9481. Min Act: -0.1700
Data Index: 5681356 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9481. Min Act: -0.1700
Data Index: 2045204 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9793. Min Act: -0.1700
Data Index: 1051983 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9481. Min Act: -0.1700
Data Index: 3541998 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9481. Min Act: -0.1700
Data Index: 79574 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9168. Min Act: -0.1700
Data Index: 4657199 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9168. Min Act: -0.1700
Data Index: 1228855 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.8543. Min Act: -0.1700
Data Index: 5744937 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.8855. Min Act: -0.1700
Data Index: 1530673 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.8855. Min Act: -0.1700
Data Index: 298647 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3544. Min Range: -4.3544
Max Act: 3.9168. Min Act: -0.1700
Data Index: 4630651 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19