Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4236 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0931. Min Act: -0.0001
Data Index: 379517 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0834. Min Act: -0.0001
Data Index: 867018 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0866. Min Act: -0.0001
Data Index: 697855 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0899. Min Act: -0.0001
Data Index: 950362 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0768. Min Act: -0.0001
Data Index: 712476 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0757. Min Act: -0.0001
Data Index: 1534506 (Python Code)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0728. Min Act: -0.0001
Data Index: 1152389 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0730. Min Act: -0.0001
Data Index: 1203654 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0716. Min Act: -0.0001
Data Index: 89735 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0685. Min Act: -0.0002
Data Index: 1236957 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0708. Min Act: -0.0001
Data Index: 28606 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0649. Min Act: -0.0001
Data Index: 1243591 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0702. Min Act: -0.0001
Data Index: 870879 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0694. Min Act: -0.0001
Data Index: 1282709 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0638. Min Act: -0.0001
Data Index: 1199930 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0631. Min Act: -0.0001
Data Index: 256782 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0674. Min Act: -0.0001
Data Index: 550680 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0604. Min Act: -0.0001
Data Index: 331 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0700. Min Act: -0.0001
Data Index: 529196 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0931. Min Range: -0.0931
Max Act: 0.0558. Min Act: -0.0001
Data Index: 295951 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19