Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.7218. Min Act: -0.1700
Data Index: 7848656 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.6281. Min Act: -0.1700
Data Index: 6521636 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5968. Min Act: -0.1700
Data Index: 6770311 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5968. Min Act: -0.1700
Data Index: 1264277 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5968. Min Act: -0.1700
Data Index: 1394373 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5656. Min Act: -0.1700
Data Index: 4747386 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5656. Min Act: -0.1700
Data Index: 8564132 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5656. Min Act: -0.1700
Data Index: 8382903 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5343. Min Act: -0.1700
Data Index: 6501620 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5343. Min Act: -0.1700
Data Index: 725490 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5031. Min Act: -0.1700
Data Index: 1254481 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5031. Min Act: -0.1700
Data Index: 5984745 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.5031. Min Act: -0.1700
Data Index: 8602303 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4718. Min Act: -0.1700
Data Index: 8303896 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4406. Min Act: -0.1700
Data Index: 6176359 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4718. Min Act: -0.1700
Data Index: 7979583 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4718. Min Act: -0.1700
Data Index: 2867075 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4406. Min Act: -0.1700
Data Index: 6224272 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4406. Min Act: -0.1700
Data Index: 6519773 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7218. Min Range: -6.7218
Max Act: 6.4406. Min Act: -0.1700
Data Index: 8398501 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19