Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5984 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.1729. Min Act: -0.1700
Data Index: 5413028 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.1415. Min Act: -0.1700
Data Index: 3693994 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.1257. Min Act: -0.1700
Data Index: 6939418 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.1100. Min Act: -0.1700
Data Index: 3993665 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.0784. Min Act: -0.1700
Data Index: 8724143 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.0784. Min Act: -0.1700
Data Index: 6464581 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.0784. Min Act: -0.1700
Data Index: 6742230 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.0784. Min Act: -0.1700
Data Index: 6846497 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.0469. Min Act: -0.1700
Data Index: 4435019 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.0627. Min Act: -0.1700
Data Index: 1666869 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.0311. Min Act: -0.1700
Data Index: 81168 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1729. Min Range: -3.1729
Max Act: 3.0153. Min Act: -0.1700
Data Index: 5806899 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1729. Min Range: -3.1729
Max Act: 2.9837. Min Act: -0.1700
Data Index: 1552803 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1729. Min Range: -3.1729
Max Act: 2.9837. Min Act: -0.1700
Data Index: 3292421 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1729. Min Range: -3.1729
Max Act: 2.9995. Min Act: -0.1700
Data Index: 911108 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1729. Min Range: -3.1729
Max Act: 2.9837. Min Act: -0.1700
Data Index: 2153903 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1729. Min Range: -3.1729
Max Act: 2.9679. Min Act: -0.1700
Data Index: 4043041 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1729. Min Range: -3.1729
Max Act: 2.9679. Min Act: -0.1700
Data Index: 509039 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1729. Min Range: -3.1729
Max Act: 2.9679. Min Act: -0.1700
Data Index: 2930056 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1729. Min Range: -3.1729
Max Act: 2.9520. Min Act: -0.1700
Data Index: 3362753 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19