Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 578 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.8521. Min Act: -0.1700
Data Index: 1680127 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.7271. Min Act: -0.1700
Data Index: 6225653 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.7271. Min Act: -0.1700
Data Index: 4173384 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.7271. Min Act: -0.1700
Data Index: 8392880 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6959. Min Act: -0.1700
Data Index: 147515 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6959. Min Act: -0.1700
Data Index: 6168808 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6959. Min Act: -0.1700
Data Index: 39708 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6334. Min Act: -0.1700
Data Index: 6839662 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6646. Min Act: -0.1700
Data Index: 3892383 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6646. Min Act: -0.1700
Data Index: 6754955 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6334. Min Act: -0.1700
Data Index: 765543 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6334. Min Act: -0.1700
Data Index: 5357389 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6334. Min Act: -0.1700
Data Index: 148029 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6334. Min Act: -0.1700
Data Index: 8809005 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.5709. Min Act: -0.1700
Data Index: 8202815 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.6021. Min Act: -0.1700
Data Index: 1113763 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.5709. Min Act: -0.1700
Data Index: 6425610 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.5396. Min Act: -0.1700
Data Index: 891851 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.5709. Min Act: -0.1700
Data Index: 6707836 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8521. Min Range: -4.8521
Max Act: 4.5396. Min Act: -0.1700
Data Index: 5012508 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19