Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2896 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.1115. Min Range: -1.1115
Max Act: 1.1115. Min Act: -0.0001
Data Index: 1552982 (Python Code)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.9540. Min Act: -0.0001
Data Index: 1151668 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1115. Min Range: -1.1115
Max Act: 1.0864. Min Act: -0.0001
Data Index: 95343 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.8295. Min Act: -0.0001
Data Index: 50287 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.7880. Min Act: -0.0001
Data Index: 273421 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.8656. Min Act: -0.0001
Data Index: 121844 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.8948. Min Act: -0.0001
Data Index: 1317104 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.8156. Min Act: -0.0001
Data Index: 1146006 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.8069. Min Act: -0.0001
Data Index: 67164 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.8816. Min Act: -0.0001
Data Index: 980794 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.7873. Min Act: -0.0001
Data Index: 375820 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.7375. Min Act: -0.0001
Data Index: 213793 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.7629. Min Act: -0.0001
Data Index: 132510 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.7458. Min Act: -0.0001
Data Index: 382059 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.7259. Min Act: -0.0001
Data Index: 1357429 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.6919. Min Act: -0.0001
Data Index: 596838 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.7093. Min Act: -0.0001
Data Index: 1064718 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.6858. Min Act: -0.0001
Data Index: 140128 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.7282. Min Act: -0.0001
Data Index: 1052354 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1115. Min Range: -1.1115
Max Act: 0.6788. Min Act: -0.0001
Data Index: 461855 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19