Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1478 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0886. Min Act: -0.0001
Data Index: 32850 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0770. Min Act: -0.0001
Data Index: 17674 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0823. Min Act: -0.0001
Data Index: 24831 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0722. Min Act: -0.0001
Data Index: 777140 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0719. Min Act: -0.0001
Data Index: 943613 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0719. Min Act: -0.0001
Data Index: 686306 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0928. Min Act: -0.0001
Data Index: 678823 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0747. Min Act: -0.0001
Data Index: 1340678 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0761. Min Act: -0.0001
Data Index: 1616790 (Python Code)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0726. Min Act: -0.0001
Data Index: 1229630 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0741. Min Act: -0.0001
Data Index: 858811 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0691. Min Act: -0.0001
Data Index: 338863 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0755. Min Act: -0.0001
Data Index: 1344020 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0757. Min Act: -0.0001
Data Index: 97941 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0752. Min Act: -0.0001
Data Index: 435501 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0745. Min Act: -0.0001
Data Index: 70444 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0740. Min Act: -0.0001
Data Index: 204544 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0544. Min Act: -0.0002
Data Index: 1623188 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0686. Min Act: -0.0001
Data Index: 409926 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0928. Min Range: -0.0928
Max Act: 0.0774. Min Act: -0.0001
Data Index: 324385 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19