Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3052 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.9660. Min Act: -0.0001
Data Index: 715805 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.9027. Min Act: -0.0001
Data Index: 47431 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.9181. Min Act: -0.0001
Data Index: 710541 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.9250. Min Act: -0.0001
Data Index: 1619290 (Python Code)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.9103. Min Act: -0.0001
Data Index: 1273744 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.9176. Min Act: -0.0001
Data Index: 1476800 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.8113. Min Act: -0.0001
Data Index: 1435575 (Python Code)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.8013. Min Act: -0.0001
Data Index: 907582 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.8206. Min Act: -0.0001
Data Index: 1421321 (Python Code)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.8163. Min Act: -0.0001
Data Index: 521725 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.7763. Min Act: -0.0001
Data Index: 35517 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.7455. Min Act: -0.0001
Data Index: 994792 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.7629. Min Act: -0.0001
Data Index: 1471546 (Python Code)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.7841. Min Act: -0.0001
Data Index: 79259 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.7812. Min Act: -0.0001
Data Index: 243213 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.7280. Min Act: -0.0001
Data Index: 148204 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.7705. Min Act: -0.0001
Data Index: 131740 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.7391. Min Act: -0.0001
Data Index: 205210 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.7402. Min Act: -0.0001
Data Index: 1158757 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9660. Min Range: -0.9660
Max Act: 0.6839. Min Act: -0.0001
Data Index: 967058 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19