Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2452 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0777. Min Act: -0.1700
Data Index: 3402676 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9526. Min Act: -0.1700
Data Index: 471583 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9526. Min Act: -0.1700
Data Index: 5614335 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9526. Min Act: -0.1700
Data Index: 8578417 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9214. Min Act: -0.1700
Data Index: 1853909 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9214. Min Act: -0.1700
Data Index: 6579344 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8901. Min Act: -0.1700
Data Index: 3780844 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8901. Min Act: -0.1700
Data Index: 4704252 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8901. Min Act: -0.1700
Data Index: 3447655 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8901. Min Act: -0.1700
Data Index: 8367332 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8901. Min Act: -0.1700
Data Index: 1965655 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8901. Min Act: -0.1700
Data Index: 45822 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8588. Min Act: -0.1700
Data Index: 1801255 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8588. Min Act: -0.1700
Data Index: 1840414 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8588. Min Act: -0.1700
Data Index: 5098616 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8588. Min Act: -0.1700
Data Index: 1702612 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8588. Min Act: -0.1700
Data Index: 6712819 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8588. Min Act: -0.1700
Data Index: 1622246 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8588. Min Act: -0.1700
Data Index: 6475810 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.8276. Min Act: -0.1700
Data Index: 411666 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19