Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 606 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.1017. Min Range: -3.1017
Max Act: 3.1017. Min Act: -0.0001
Data Index: 90173 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1017. Min Range: -3.1017
Max Act: 3.0766. Min Act: -0.0001
Data Index: 653536 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.9671. Min Act: -0.0001
Data Index: 417396 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1017. Min Range: -3.1017
Max Act: 3.0502. Min Act: -0.0001
Data Index: 673207 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1017. Min Range: -3.1017
Max Act: 3.0383. Min Act: -0.0001
Data Index: 1992 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1017. Min Range: -3.1017
Max Act: 3.0183. Min Act: -0.0001
Data Index: 1184985 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.7834. Min Act: -0.0001
Data Index: 1060639 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.8332. Min Act: -0.0001
Data Index: 622284 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.6480. Min Act: -0.0001
Data Index: 359663 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.5157. Min Act: -0.0001
Data Index: 1059005 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.6073. Min Act: -0.0001
Data Index: 676828 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.7589. Min Act: -0.0001
Data Index: 494390 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.6679. Min Act: -0.0001
Data Index: 775975 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.6436. Min Act: -0.0001
Data Index: 13644 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.8271. Min Act: -0.0001
Data Index: 927854 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.6533. Min Act: -0.0001
Data Index: 908594 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.6308. Min Act: -0.0001
Data Index: 1121724 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.5745. Min Act: -0.0001
Data Index: 328587 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.6372. Min Act: -0.0001
Data Index: 635937 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1017. Min Range: -3.1017
Max Act: 2.2982. Min Act: -0.0001
Data Index: 980850 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19