Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1918 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.9595. Min Act: -0.1700
Data Index: 8551869 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.8970. Min Act: -0.1700
Data Index: 5952542 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.7720. Min Act: -0.1700
Data Index: 4439254 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.6470. Min Act: -0.1700
Data Index: 274206 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5845. Min Act: -0.1700
Data Index: 8777458 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5220. Min Act: -0.1700
Data Index: 9805 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5845. Min Act: -0.1700
Data Index: 8513060 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5220. Min Act: -0.1700
Data Index: 2756691 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5220. Min Act: -0.1700
Data Index: 4960574 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.4595. Min Act: -0.1700
Data Index: 6958166 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5220. Min Act: -0.1700
Data Index: 1365739 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.4595. Min Act: -0.1700
Data Index: 7716904 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5220. Min Act: -0.1700
Data Index: 7278663 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5220. Min Act: -0.1700
Data Index: 574494 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5220. Min Act: -0.1700
Data Index: 5375 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.5845. Min Act: -0.1700
Data Index: 7006462 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.4595. Min Act: -0.1700
Data Index: 2945865 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.4595. Min Act: -0.1700
Data Index: 8224806 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.4595. Min Act: -0.1699
Data Index: 7090277 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9595. Min Range: -10.9595
Max Act: 10.3970. Min Act: -0.1700
Data Index: 4293987 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19