Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1856 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2300. Min Range: -5.2300
Max Act: 5.2300. Min Act: -0.1700
Data Index: 8140642 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2300. Min Range: -5.2300
Max Act: 5.1363. Min Act: -0.1700
Data Index: 3436793 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.9488. Min Act: -0.1700
Data Index: 7434608 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.9488. Min Act: -0.1700
Data Index: 2512053 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.9175. Min Act: -0.1700
Data Index: 6990965 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.9175. Min Act: -0.1700
Data Index: 4661017 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.8550. Min Act: -0.1700
Data Index: 2371893 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.8238. Min Act: -0.1700
Data Index: 1508891 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.8238. Min Act: -0.1700
Data Index: 5105521 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.8238. Min Act: -0.1700
Data Index: 1386007 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.7613. Min Act: -0.1700
Data Index: 4016741 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.7925. Min Act: -0.1700
Data Index: 2226720 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.7925. Min Act: -0.1700
Data Index: 4025196 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.7925. Min Act: -0.1700
Data Index: 5935303 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.7300. Min Act: -0.1700
Data Index: 763577 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.7300. Min Act: -0.1700
Data Index: 801000 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.7300. Min Act: -0.1700
Data Index: 1532302 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.6988. Min Act: -0.1700
Data Index: 1463829 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.6988. Min Act: -0.1700
Data Index: 524307 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2300. Min Range: -5.2300
Max Act: 4.6988. Min Act: -0.1700
Data Index: 5405370 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19