Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 635 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3591. Min Range: -2.3591
Max Act: 2.3591. Min Act: -0.0001
Data Index: 240635 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3591. Min Range: -2.3591
Max Act: 2.2410. Min Act: -0.0001
Data Index: 1032696 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3591. Min Range: -2.3591
Max Act: 2.2359. Min Act: -0.0001
Data Index: 734378 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3591. Min Range: -2.3591
Max Act: 2.2430. Min Act: -0.0000
Data Index: 1404107 (Python Code)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3591. Min Range: -2.3591
Max Act: 2.2235. Min Act: -0.0001
Data Index: 1276750 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3591. Min Range: -2.3591
Max Act: 2.1641. Min Act: -0.0001
Data Index: 184694 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3591. Min Range: -2.3591
Max Act: 2.0051. Min Act: -0.0001
Data Index: 977282 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3591. Min Range: -2.3591
Max Act: 2.0477. Min Act: -0.0001
Data Index: 1503386 (Python Code)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.9564. Min Act: -0.0000
Data Index: 1349768 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.8427. Min Act: -0.0000
Data Index: 751729 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.6174. Min Act: -0.0001
Data Index: 725282 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.7227. Min Act: -0.0001
Data Index: 371855 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.7008. Min Act: -0.0001
Data Index: 553380 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.6904. Min Act: -0.0001
Data Index: 393231 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.6926. Min Act: -0.0001
Data Index: 810193 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.6787. Min Act: -0.0000
Data Index: 1161529 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.7583. Min Act: -0.0001
Data Index: 198129 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.6471. Min Act: -0.0000
Data Index: 1329073 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.6140. Min Act: -0.0001
Data Index: 358205 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3591. Min Range: -2.3591
Max Act: 1.6050. Min Act: -0.0001
Data Index: 980351 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19