Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4349 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.5457. Min Act: -0.0001
Data Index: 196668 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.2706. Min Act: -0.0001
Data Index: 713578 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.1902. Min Act: -0.0001
Data Index: 854667 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.0377. Min Act: -0.0001
Data Index: 1106136 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.1417. Min Act: -0.0001
Data Index: 227679 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5457. Min Range: -2.5457
Max Act: 1.9682. Min Act: -0.0001
Data Index: 946696 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.1094. Min Act: -0.0001
Data Index: 852413 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5457. Min Range: -2.5457
Max Act: 1.9702. Min Act: -0.0001
Data Index: 373389 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5457. Min Range: -2.5457
Max Act: 1.8875. Min Act: -0.0001
Data Index: 166655 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.0846. Min Act: -0.0001
Data Index: 582008 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.1967. Min Act: -0.0002
Data Index: 598903 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.1213. Min Act: -0.0001
Data Index: 332126 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.0172. Min Act: -0.0001
Data Index: 386865 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.0452. Min Act: -0.0001
Data Index: 1178534 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.0176. Min Act: -0.0001
Data Index: 215009 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.0746. Min Act: -0.0001
Data Index: 449795 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5457. Min Range: -2.5457
Max Act: 1.9617. Min Act: -0.0001
Data Index: 1204183 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.2338. Min Act: -0.0001
Data Index: 170367 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.0646. Min Act: -0.0001
Data Index: 702696 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5457. Min Range: -2.5457
Max Act: 2.0411. Min Act: -0.0001
Data Index: 85359 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19