Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3833 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.6799. Min Act: -0.0001
Data Index: 632085 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.6087. Min Act: -0.0001
Data Index: 1357139 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.1048. Min Act: -0.0001
Data Index: 155275 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.6708. Min Act: -0.0001
Data Index: 580519 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.3787. Min Act: -0.0001
Data Index: 679002 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.1278. Min Act: -0.0001
Data Index: 926929 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.2102. Min Act: -0.0001
Data Index: 45448 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.2023. Min Act: -0.0001
Data Index: 358390 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.4521. Min Act: -0.0001
Data Index: 479047 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.2511. Min Act: -0.0001
Data Index: 1082997 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6799. Min Range: -9.6799
Max Act: 8.8227. Min Act: -0.0001
Data Index: 1293046 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6799. Min Range: -9.6799
Max Act: 8.9072. Min Act: -0.0001
Data Index: 765307 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6799. Min Range: -9.6799
Max Act: 8.9900. Min Act: -0.0001
Data Index: 169858 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6799. Min Range: -9.6799
Max Act: 9.2559. Min Act: -0.0001
Data Index: 981236 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6799. Min Range: -9.6799
Max Act: 8.8674. Min Act: -0.0001
Data Index: 312259 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6799. Min Range: -9.6799
Max Act: 8.8500. Min Act: -0.0001
Data Index: 1258480 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6799. Min Range: -9.6799
Max Act: 8.9263. Min Act: -0.0001
Data Index: 1339899 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6799. Min Range: -9.6799
Max Act: 8.8678. Min Act: -0.0001
Data Index: 1172518 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6799. Min Range: -9.6799
Max Act: 8.3928. Min Act: -0.0001
Data Index: 833527 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6799. Min Range: -9.6799
Max Act: 8.6781. Min Act: -0.0001
Data Index: 1345873 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19