Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3004 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.7480. Min Act: -0.0001
Data Index: 1220370 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.4905. Min Act: -0.0001
Data Index: 1281780 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.7467. Min Act: -0.0001
Data Index: 1343917 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.2787. Min Act: -0.0001
Data Index: 1144849 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.0945. Min Act: -0.0001
Data Index: 389287 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.4237. Min Act: -0.0001
Data Index: 1096038 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.2726. Min Act: -0.0001
Data Index: 1071709 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.1847. Min Act: -0.0001
Data Index: 193569 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7480. Min Range: -2.7480
Max Act: 1.9765. Min Act: -0.0001
Data Index: 346793 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.1734. Min Act: -0.0001
Data Index: 49584 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.2614. Min Act: -0.0001
Data Index: 541866 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.3313. Min Act: -0.0001
Data Index: 833040 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.1087. Min Act: -0.0001
Data Index: 867616 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.4157. Min Act: -0.0001
Data Index: 502924 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.3008. Min Act: -0.0001
Data Index: 608040 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.2640. Min Act: -0.0001
Data Index: 1290966 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.3024. Min Act: -0.0001
Data Index: 817230 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.0623. Min Act: -0.0001
Data Index: 692053 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.3546. Min Act: -0.0001
Data Index: 257642 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7480. Min Range: -2.7480
Max Act: 2.1196. Min Act: -0.0001
Data Index: 1052340 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19