Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2990 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5384. Min Range: -1.5384
Max Act: 1.5384. Min Act: -0.0001
Data Index: 152069 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5384. Min Range: -1.5384
Max Act: 1.1089. Min Act: -0.0001
Data Index: 68620 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9884. Min Act: -0.0001
Data Index: 840586 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.8977. Min Act: -0.0001
Data Index: 1021048 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9445. Min Act: -0.0001
Data Index: 1249430 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9710. Min Act: -0.0001
Data Index: 804312 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5384. Min Range: -1.5384
Max Act: 1.0105. Min Act: -0.0001
Data Index: 323907 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9102. Min Act: -0.0001
Data Index: 360266 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9610. Min Act: -0.0001
Data Index: 313139 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9550. Min Act: -0.0001
Data Index: 662621 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9266. Min Act: -0.0001
Data Index: 273033 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9659. Min Act: -0.0001
Data Index: 737580 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.8552. Min Act: -0.0001
Data Index: 575661 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9329. Min Act: -0.0001
Data Index: 788511 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.8393. Min Act: -0.0001
Data Index: 936610 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.8055. Min Act: -0.0001
Data Index: 795637 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.9417. Min Act: -0.0001
Data Index: 607812 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.7779. Min Act: -0.0001
Data Index: 1279525 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.8356. Min Act: -0.0001
Data Index: 1000878 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5384. Min Range: -1.5384
Max Act: 0.8128. Min Act: -0.0001
Data Index: 194852 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19