Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4021 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.8425. Min Act: -0.1700
Data Index: 5508277 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.6550. Min Act: -0.1700
Data Index: 5356275 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.2800. Min Act: -0.1700
Data Index: 5277954 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.2800. Min Act: -0.1700
Data Index: 8166883 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.2800. Min Act: -0.1700
Data Index: 4964352 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.2175. Min Act: -0.1700
Data Index: 4271572 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.1550. Min Act: -0.1700
Data Index: 7454121 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.1550. Min Act: -0.1700
Data Index: 1026891 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.1550. Min Act: -0.1700
Data Index: 6387898 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.1550. Min Act: -0.1700
Data Index: 5783814 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.0925. Min Act: -0.1700
Data Index: 5333851 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.0925. Min Act: -0.1700
Data Index: 115176 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.0925. Min Act: -0.1700
Data Index: 5541584 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8425. Min Range: -9.8425
Max Act: 9.0300. Min Act: -0.1700
Data Index: 5294611 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8425. Min Range: -9.8425
Max Act: 8.9675. Min Act: -0.1700
Data Index: 2004416 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8425. Min Range: -9.8425
Max Act: 8.9675. Min Act: -0.1700
Data Index: 1406835 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8425. Min Range: -9.8425
Max Act: 8.9050. Min Act: -0.1700
Data Index: 2929010 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8425. Min Range: -9.8425
Max Act: 8.9050. Min Act: -0.1700
Data Index: 7102629 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8425. Min Range: -9.8425
Max Act: 8.9050. Min Act: -0.1700
Data Index: 5655602 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8425. Min Range: -9.8425
Max Act: 8.9050. Min Act: -0.1700
Data Index: 1995335 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19