Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6010 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7560. Min Range: -2.7560
Max Act: 2.7560. Min Act: -0.0001
Data Index: 294545 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7560. Min Range: -2.7560
Max Act: 2.4321. Min Act: -0.0001
Data Index: 148998 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7560. Min Range: -2.7560
Max Act: 2.4926. Min Act: -0.0002
Data Index: 1019358 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7560. Min Range: -2.7560
Max Act: 1.9806. Min Act: -0.0001
Data Index: 478884 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7560. Min Range: -2.7560
Max Act: 1.7921. Min Act: -0.0001
Data Index: 1540841 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7560. Min Range: -2.7560
Max Act: 1.5183. Min Act: -0.0001
Data Index: 903541 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7560. Min Range: -2.7560
Max Act: 1.5344. Min Act: -0.0001
Data Index: 1004838 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7560. Min Range: -2.7560
Max Act: 1.3067. Min Act: -0.0001
Data Index: 1308 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7560. Min Range: -2.7560
Max Act: 1.3026. Min Act: -0.0001
Data Index: 942484 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7560. Min Range: -2.7560
Max Act: 1.2079. Min Act: -0.0001
Data Index: 134956 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7560. Min Range: -2.7560
Max Act: 0.9595. Min Act: -0.0001
Data Index: 349581 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7560. Min Range: -2.7560
Max Act: 1.2681. Min Act: -0.0001
Data Index: 1086003 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7560. Min Range: -2.7560
Max Act: 0.3568. Min Act: -0.0001
Data Index: 1067617 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7560. Min Range: -2.7560
Max Act: 0.8184. Min Act: -0.0001
Data Index: 47461 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7560. Min Range: -2.7560
Max Act: 0.9890. Min Act: -0.0001
Data Index: 101308 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7560. Min Range: -2.7560
Max Act: 0.5198. Min Act: -0.0001
Data Index: 664350 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7560. Min Range: -2.7560
Max Act: 0.4575. Min Act: -0.0001
Data Index: 588940 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7560. Min Range: -2.7560
Max Act: 0.4065. Min Act: -0.0001
Data Index: 747114 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7560. Min Range: -2.7560
Max Act: 0.4455. Min Act: -0.0001
Data Index: 1405737 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7560. Min Range: -2.7560
Max Act: 0.4503. Min Act: -0.0001
Data Index: 62404 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19