Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2162 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.8796. Min Act: -0.0001
Data Index: 553136 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.8038. Min Act: -0.0001
Data Index: 806051 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.7516. Min Act: -0.0001
Data Index: 690170 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.7395. Min Act: -0.0001
Data Index: 60135 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.7567. Min Act: -0.0001
Data Index: 429444 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.7081. Min Act: -0.0001
Data Index: 60073 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.7034. Min Act: -0.0001
Data Index: 1226861 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6980. Min Act: -0.0001
Data Index: 88718 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.7179. Min Act: -0.0001
Data Index: 1022054 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6818. Min Act: -0.0001
Data Index: 1031327 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.7211. Min Act: -0.0001
Data Index: 1099771 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.7626. Min Act: -0.0001
Data Index: 903340 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6701. Min Act: -0.0001
Data Index: 355576 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6590. Min Act: -0.0001
Data Index: 688271 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6470. Min Act: -0.0001
Data Index: 1154140 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6653. Min Act: -0.0001
Data Index: 1339757 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6451. Min Act: -0.0001
Data Index: 141627 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6376. Min Act: -0.0001
Data Index: 827526 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6840. Min Act: -0.0001
Data Index: 1102301 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8796. Min Range: -0.8796
Max Act: 0.6904. Min Act: -0.0001
Data Index: 1350040 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19