Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3099 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.9826. Min Act: -0.0001
Data Index: 849371 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.7389. Min Act: -0.0001
Data Index: 315821 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.7315. Min Act: -0.0001
Data Index: 1319282 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.6987. Min Act: -0.0001
Data Index: 400686 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.4518. Min Act: -0.0001
Data Index: 1111500 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.3747. Min Act: -0.0001
Data Index: 1229784 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.5923. Min Act: -0.0001
Data Index: 74881 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.6919. Min Act: -0.0001
Data Index: 566004 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.3689. Min Act: -0.0001
Data Index: 1125217 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.4709. Min Act: -0.0001
Data Index: 1070599 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.2600. Min Act: -0.0001
Data Index: 870557 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.1507. Min Act: -0.0001
Data Index: 16054 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.1795. Min Act: -0.0001
Data Index: 831320 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.1862. Min Act: -0.0001
Data Index: 906520 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.1916. Min Act: -0.0001
Data Index: 843756 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.1713. Min Act: -0.0001
Data Index: 147881 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.1410. Min Act: -0.0001
Data Index: 781499 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.0931. Min Act: -0.0001
Data Index: 1041696 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9826. Min Range: -2.9826
Max Act: 2.1453. Min Act: -0.0001
Data Index: 806652 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9826. Min Range: -2.9826
Max Act: 1.9246. Min Act: -0.0001
Data Index: 347345 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19