Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3541 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.7068. Min Act: -0.0001
Data Index: 46942 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.7651. Min Act: -0.0001
Data Index: 671468 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.4751. Min Act: -0.0001
Data Index: 309365 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.6305. Min Act: -0.0001
Data Index: 415119 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.4269. Min Act: -0.0001
Data Index: 782167 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.5436. Min Act: -0.0001
Data Index: 583235 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.4907. Min Act: -0.0001
Data Index: 259485 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.4760. Min Act: -0.0001
Data Index: 156740 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.4798. Min Act: -0.0001
Data Index: 1002377 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.5330. Min Act: -0.0001
Data Index: 751388 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.5275. Min Act: -0.0001
Data Index: 480246 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.4157. Min Act: -0.0001
Data Index: 982771 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.2867. Min Act: -0.0001
Data Index: 765126 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.3769. Min Act: -0.0001
Data Index: 323592 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.3597. Min Act: -0.0001
Data Index: 616658 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.1171. Min Act: -0.0001
Data Index: 840122 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.3632. Min Act: -0.0001
Data Index: 264043 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.2521. Min Act: -0.0001
Data Index: 1239308 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.2041. Min Act: -0.0001
Data Index: 290690 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7651. Min Range: -2.7651
Max Act: 2.3004. Min Act: -0.0001
Data Index: 366245 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19