Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 9 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.6029. Min Act: -0.0001
Data Index: 764303 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5772. Min Act: -0.0001
Data Index: 721499 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5468. Min Act: -0.0001
Data Index: 528541 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5693. Min Act: -0.0001
Data Index: 424462 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5207. Min Act: -0.0001
Data Index: 478582 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5428. Min Act: -0.0001
Data Index: 667025 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5189. Min Act: -0.0001
Data Index: 30980 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5314. Min Act: -0.0001
Data Index: 1051047 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5142. Min Act: -0.0001
Data Index: 210517 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.6004. Min Act: -0.0001
Data Index: 1175394 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5019. Min Act: -0.0001
Data Index: 553666 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5303. Min Act: -0.0001
Data Index: 1232107 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5205. Min Act: -0.0001
Data Index: 242657 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.4974. Min Act: -0.0001
Data Index: 676597 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5054. Min Act: -0.0001
Data Index: 348351 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5165. Min Act: -0.0001
Data Index: 613170 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.5127. Min Act: -0.0001
Data Index: 523179 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.4572. Min Act: -0.0001
Data Index: 932263 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.4695. Min Act: -0.0001
Data Index: 331826 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6029. Min Range: -0.6029
Max Act: 0.4881. Min Act: -0.0001
Data Index: 787944 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19