Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2533 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.4368. Min Act: -0.1700
Data Index: 343847 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.3118. Min Act: -0.1700
Data Index: 3330282 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.2493. Min Act: -0.1700
Data Index: 2360305 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.1556. Min Act: -0.1700
Data Index: 4619136 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.1556. Min Act: -0.1700
Data Index: 7548754 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.1243. Min Act: -0.1700
Data Index: 5283591 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.1243. Min Act: -0.1700
Data Index: 1740770 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.0306. Min Act: -0.1700
Data Index: 1360112 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.0306. Min Act: -0.1700
Data Index: 5546239 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.0306. Min Act: -0.1700
Data Index: 2946631 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.0306. Min Act: -0.1700
Data Index: 8064054 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4368. Min Range: -5.4368
Max Act: 5.0306. Min Act: -0.1700
Data Index: 4482563 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4368. Min Range: -5.4368
Max Act: 4.9993. Min Act: -0.1700
Data Index: 7251205 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4368. Min Range: -5.4368
Max Act: 4.9993. Min Act: -0.1700
Data Index: 5935684 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4368. Min Range: -5.4368
Max Act: 4.9993. Min Act: -0.1700
Data Index: 2133628 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4368. Min Range: -5.4368
Max Act: 4.9681. Min Act: -0.1700
Data Index: 1477918 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4368. Min Range: -5.4368
Max Act: 4.9681. Min Act: -0.1700
Data Index: 6532754 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4368. Min Range: -5.4368
Max Act: 4.9681. Min Act: -0.1700
Data Index: 6629115 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4368. Min Range: -5.4368
Max Act: 4.9681. Min Act: -0.1700
Data Index: 1520334 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4368. Min Range: -5.4368
Max Act: 4.9993. Min Act: -0.1700
Data Index: 3436789 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19