Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4481 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.6423. Min Range: -3.6423
Max Act: 3.6423. Min Act: -0.0001
Data Index: 351881 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6423. Min Range: -3.6423
Max Act: 3.2739. Min Act: -0.0001
Data Index: 694673 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.8135. Min Act: -0.0001
Data Index: 118683 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.8406. Min Act: -0.0001
Data Index: 318835 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.5738. Min Act: -0.0001
Data Index: 1124763 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.7103. Min Act: -0.0001
Data Index: 832107 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.3518. Min Act: -0.0001
Data Index: 1193999 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.5748. Min Act: -0.0001
Data Index: 528641 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.6698. Min Act: -0.0001
Data Index: 1005877 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.6759. Min Act: -0.0001
Data Index: 1055295 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.5374. Min Act: -0.0001
Data Index: 941008 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.4047. Min Act: -0.0001
Data Index: 29196 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.2617. Min Act: -0.0001
Data Index: 501693 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.2266. Min Act: -0.0001
Data Index: 1168911 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.5729. Min Act: -0.0001
Data Index: 1338910 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.1374. Min Act: -0.0001
Data Index: 400130 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.1642. Min Act: -0.0001
Data Index: 343189 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.2329. Min Act: -0.0001
Data Index: 956507 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.3462. Min Act: -0.0001
Data Index: 976091 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6423. Min Range: -3.6423
Max Act: 2.2056. Min Act: -0.0001
Data Index: 1102647 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19