Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5104 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.9625. Min Act: -0.0001
Data Index: 1197613 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.6016. Min Act: -0.0001
Data Index: 558086 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.2424. Min Act: -0.0001
Data Index: 196569 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.4139. Min Act: -0.0001
Data Index: 78028 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.1776. Min Act: -0.0001
Data Index: 842359 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.1717. Min Act: -0.0001
Data Index: 892507 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.1643. Min Act: -0.0001
Data Index: 686157 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.0122. Min Act: -0.0001
Data Index: 978374 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.1827. Min Act: -0.0001
Data Index: 1144503 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.3963. Min Act: -0.0001
Data Index: 4631 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.0454. Min Act: -0.0001
Data Index: 912040 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9625. Min Range: -2.9625
Max Act: 1.8496. Min Act: -0.0001
Data Index: 1206005 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9625. Min Range: -2.9625
Max Act: 1.8525. Min Act: -0.0001
Data Index: 1096415 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.0295. Min Act: -0.0001
Data Index: 463788 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9625. Min Range: -2.9625
Max Act: 1.8017. Min Act: -0.0001
Data Index: 996487 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9625. Min Range: -2.9625
Max Act: 2.2337. Min Act: -0.0001
Data Index: 96193 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9625. Min Range: -2.9625
Max Act: 1.8883. Min Act: -0.0001
Data Index: 1092808 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9625. Min Range: -2.9625
Max Act: 1.9484. Min Act: -0.0001
Data Index: 302421 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9625. Min Range: -2.9625
Max Act: 1.8348. Min Act: -0.0001
Data Index: 968231 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9625. Min Range: -2.9625
Max Act: 1.8475. Min Act: -0.0001
Data Index: 534964 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19