Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4316 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.4826. Min Act: -0.0001
Data Index: 700778 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3991. Min Act: -0.0001
Data Index: 424617 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.4445. Min Act: -0.0001
Data Index: 637360 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3584. Min Act: -0.0001
Data Index: 1452049 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.4068. Min Act: -0.0001
Data Index: 649995 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3811. Min Act: -0.0001
Data Index: 1480113 (Python Code)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3691. Min Act: -0.0001
Data Index: 1109761 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3430. Min Act: -0.0001
Data Index: 219534 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3658. Min Act: -0.0001
Data Index: 1628340 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3333. Min Act: -0.0001
Data Index: 477739 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3644. Min Act: -0.0001
Data Index: 1505871 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.2901. Min Act: -0.0001
Data Index: 1197017 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3728. Min Act: -0.0001
Data Index: 79576 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3541. Min Act: -0.0001
Data Index: 1431509 (Python Code)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3779. Min Act: -0.0001
Data Index: 849577 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3519. Min Act: -0.0001
Data Index: 587154 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3215. Min Act: -0.0001
Data Index: 171022 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3300. Min Act: -0.0001
Data Index: 294616 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3519. Min Act: -0.0001
Data Index: 1310120 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4826. Min Range: -0.4826
Max Act: 0.3854. Min Act: -0.0001
Data Index: 1065353 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19