Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3996 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.8038. Min Act: -0.0001
Data Index: 376740 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.7491. Min Act: -0.0001
Data Index: 68118 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.7573. Min Act: -0.0001
Data Index: 881194 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.7265. Min Act: -0.0001
Data Index: 164192 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.7008. Min Act: -0.0001
Data Index: 1480219 (Python Code)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.7086. Min Act: -0.0001
Data Index: 1020561 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6708. Min Act: -0.0001
Data Index: 1400707 (Python Code)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6840. Min Act: -0.0001
Data Index: 302511 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6681. Min Act: -0.0001
Data Index: 817192 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6449. Min Act: -0.0001
Data Index: 889620 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.5974. Min Act: -0.0001
Data Index: 1205473 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6121. Min Act: -0.0001
Data Index: 796199 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6061. Min Act: -0.0001
Data Index: 221978 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6019. Min Act: -0.0001
Data Index: 347009 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6016. Min Act: -0.0001
Data Index: 676 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.5823. Min Act: -0.0001
Data Index: 620728 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.5924. Min Act: -0.0001
Data Index: 797715 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6126. Min Act: -0.0001
Data Index: 968209 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.5953. Min Act: -0.0001
Data Index: 1266867 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8038. Min Range: -0.8038
Max Act: 0.6007. Min Act: -0.0001
Data Index: 88380 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19