Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2580 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.2859. Min Act: -0.0001
Data Index: 1111432 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1534. Min Act: -0.0001
Data Index: 1331270 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1181. Min Act: -0.0001
Data Index: 649074 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.2341. Min Act: -0.0001
Data Index: 262828 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2859. Min Range: -1.2859
Max Act: 0.9178. Min Act: -0.0001
Data Index: 47777 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.0781. Min Act: -0.0001
Data Index: 944359 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1406. Min Act: -0.0001
Data Index: 835175 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1071. Min Act: -0.0001
Data Index: 676479 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1383. Min Act: -0.0001
Data Index: 78864 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1265. Min Act: -0.0001
Data Index: 806312 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.0852. Min Act: -0.0001
Data Index: 232096 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1167. Min Act: -0.0001
Data Index: 782662 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.0818. Min Act: -0.0001
Data Index: 753188 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1135. Min Act: -0.0001
Data Index: 140305 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.0737. Min Act: -0.0001
Data Index: 1125514 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.0739. Min Act: -0.0001
Data Index: 968321 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1024. Min Act: -0.0001
Data Index: 840615 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.0909. Min Act: -0.0001
Data Index: 691651 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.1216. Min Act: -0.0001
Data Index: 237268 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2859. Min Range: -1.2859
Max Act: 1.0884. Min Act: -0.0001
Data Index: 434575 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19