Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3321 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0761. Min Act: -0.0001
Data Index: 969876 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0819. Min Act: -0.0001
Data Index: 1016205 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0729. Min Act: -0.0001
Data Index: 19328 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0703. Min Act: -0.0001
Data Index: 108395 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0681. Min Act: -0.0001
Data Index: 694038 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0629. Min Act: -0.0001
Data Index: 133164 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0578. Min Act: -0.0001
Data Index: 1192743 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0626. Min Act: -0.0001
Data Index: 255220 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0579. Min Act: -0.0001
Data Index: 414598 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0643. Min Act: -0.0001
Data Index: 952197 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0666. Min Act: -0.0001
Data Index: 548849 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0649. Min Act: -0.0001
Data Index: 1177185 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0616. Min Act: -0.0001
Data Index: 942675 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0588. Min Act: -0.0001
Data Index: 177577 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0580. Min Act: -0.0002
Data Index: 179848 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0601. Min Act: -0.0001
Data Index: 1136517 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0629. Min Act: -0.0001
Data Index: 9347 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0675. Min Act: -0.0001
Data Index: 647025 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0624. Min Act: -0.0001
Data Index: 1339592 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0819. Min Range: -0.0819
Max Act: 0.0613. Min Act: -0.0001
Data Index: 303540 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19