Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2419 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0615. Min Range: -6.0615
Max Act: 6.0615. Min Act: -0.1700
Data Index: 7652712 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.9990. Min Act: -0.1700
Data Index: 6790881 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.9053. Min Act: -0.1700
Data Index: 6779380 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.8740. Min Act: -0.1700
Data Index: 1248480 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.8740. Min Act: -0.1700
Data Index: 8752236 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.8740. Min Act: -0.1700
Data Index: 5894257 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.8428. Min Act: -0.1700
Data Index: 593129 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.8115. Min Act: -0.1700
Data Index: 4768581 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.8428. Min Act: -0.1700
Data Index: 6699679 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.8115. Min Act: -0.1700
Data Index: 7123951 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.8115. Min Act: -0.1700
Data Index: 2986570 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.7803. Min Act: -0.1700
Data Index: 7441064 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.7490. Min Act: -0.1700
Data Index: 4960426 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.7490. Min Act: -0.1700
Data Index: 5838702 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.7490. Min Act: -0.1700
Data Index: 6315219 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.7490. Min Act: -0.1700
Data Index: 2560574 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.7490. Min Act: -0.1700
Data Index: 8328964 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.7490. Min Act: -0.1700
Data Index: 4026520 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.7490. Min Act: -0.1700
Data Index: 1057225 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0615. Min Range: -6.0615
Max Act: 5.7178. Min Act: -0.1700
Data Index: 5927800 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19