Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4900 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.8668. Min Act: -0.0001
Data Index: 174932 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.6092. Min Act: -0.0001
Data Index: 822605 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.8423. Min Act: -0.0001
Data Index: 158520 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.6605. Min Act: -0.0001
Data Index: 1576974 (Python Code)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.6498. Min Act: -0.0001
Data Index: 908693 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.5191. Min Act: -0.0001
Data Index: 1050740 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.4876. Min Act: -0.0001
Data Index: 337004 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.1547. Min Act: -0.0001
Data Index: 794369 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.3640. Min Act: -0.0001
Data Index: 993325 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.3383. Min Act: -0.0001
Data Index: 556382 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.1595. Min Act: -0.0001
Data Index: 705357 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.2830. Min Act: -0.0001
Data Index: 1397253 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.0562. Min Act: -0.0001
Data Index: 140102 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.1213. Min Act: -0.0001
Data Index: 1156975 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8668. Min Range: -2.8668
Max Act: 1.9557. Min Act: -0.0001
Data Index: 1208176 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.0546. Min Act: -0.0001
Data Index: 1029841 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.0193. Min Act: -0.0001
Data Index: 1256896 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8668. Min Range: -2.8668
Max Act: 2.1069. Min Act: -0.0001
Data Index: 348589 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8668. Min Range: -2.8668
Max Act: 1.9922. Min Act: -0.0001
Data Index: 417349 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8668. Min Range: -2.8668
Max Act: 1.9973. Min Act: -0.0001
Data Index: 1238790 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19