Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3589 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.6200. Min Act: -0.0001
Data Index: 730809 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.4832. Min Act: -0.0001
Data Index: 1058183 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.4811. Min Act: -0.0001
Data Index: 207044 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.3889. Min Act: -0.0001
Data Index: 1362205 (Python Code)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.3700. Min Act: -0.0001
Data Index: 908016 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.4003. Min Act: -0.0001
Data Index: 376379 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.3572. Min Act: -0.0001
Data Index: 951655 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.4234. Min Act: -0.0001
Data Index: 564872 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.1882. Min Act: -0.0001
Data Index: 22034 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.3423. Min Act: -0.0001
Data Index: 1024912 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.4084. Min Act: -0.0001
Data Index: 361647 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.4294. Min Act: -0.0001
Data Index: 1226754 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.4450. Min Act: -0.0001
Data Index: 105280 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.3502. Min Act: -0.0001
Data Index: 197590 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.3142. Min Act: -0.0001
Data Index: 131427 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.2659. Min Act: -0.0001
Data Index: 21753 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.1697. Min Act: -0.0001
Data Index: 500186 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.3291. Min Act: -0.0001
Data Index: 649181 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.3416. Min Act: -0.0001
Data Index: 68628 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6200. Min Range: -1.6200
Max Act: 1.2906. Min Act: -0.0001
Data Index: 85733 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19