Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1745 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3936. Min Range: -2.3936
Max Act: 2.1517. Min Act: -0.0001
Data Index: 283298 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3936. Min Range: -2.3936
Max Act: 2.3936. Min Act: -0.0000
Data Index: 954361 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.6941. Min Act: -0.0001
Data Index: 704130 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.7854. Min Act: -0.0001
Data Index: 1348356 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.7562. Min Act: -0.0001
Data Index: 647344 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.6755. Min Act: -0.0001
Data Index: 235218 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.6478. Min Act: -0.0001
Data Index: 717732 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.7255. Min Act: -0.0001
Data Index: 1248784 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.6006. Min Act: -0.0001
Data Index: 1056491 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.5994. Min Act: -0.0001
Data Index: 445273 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.4234. Min Act: -0.0001
Data Index: 812168 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.3767. Min Act: -0.0001
Data Index: 284068 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.5447. Min Act: -0.0001
Data Index: 787741 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.5085. Min Act: -0.0001
Data Index: 1075668 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.4375. Min Act: -0.0001
Data Index: 173933 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.5550. Min Act: -0.0001
Data Index: 538742 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.0786. Min Act: -0.0000
Data Index: 286580 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.5278. Min Act: -0.0001
Data Index: 704978 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.4432. Min Act: -0.0001
Data Index: 466504 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3936. Min Range: -2.3936
Max Act: 1.4340. Min Act: -0.0000
Data Index: 598137 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19