Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 29 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 6.8537. Min Range: -6.8537
Max Act: 6.8537. Min Act: -0.0001
Data Index: 320357 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8537. Min Range: -6.8537
Max Act: 6.4949. Min Act: -0.0001
Data Index: 1070845 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.8704. Min Act: -0.0001
Data Index: 154462 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8537. Min Range: -6.8537
Max Act: 6.0002. Min Act: -0.0001
Data Index: 561331 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8537. Min Range: -6.8537
Max Act: 6.0734. Min Act: -0.0001
Data Index: 505112 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.6480. Min Act: -0.0001
Data Index: 985729 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.6497. Min Act: -0.0001
Data Index: 835542 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.2499. Min Act: -0.0001
Data Index: 9555 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.1811. Min Act: -0.0001
Data Index: 814060 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8537. Min Range: -6.8537
Max Act: 6.2262. Min Act: -0.0001
Data Index: 859074 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.4226. Min Act: -0.0001
Data Index: 751862 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.7440. Min Act: -0.0001
Data Index: 1224978 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.2048. Min Act: -0.0001
Data Index: 1202660 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.4435. Min Act: -0.0001
Data Index: 956159 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8537. Min Range: -6.8537
Max Act: 4.6005. Min Act: -0.0001
Data Index: 1286747 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.5214. Min Act: -0.0001
Data Index: 29714 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.1040. Min Act: -0.0001
Data Index: 330325 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.2928. Min Act: -0.0001
Data Index: 1185314 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.3687. Min Act: -0.0001
Data Index: 1254297 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8537. Min Range: -6.8537
Max Act: 5.0132. Min Act: -0.0001
Data Index: 965875 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19