Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4061 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.2724. Min Act: -0.0001
Data Index: 125157 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.2586. Min Act: -0.0001
Data Index: 859863 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.2711. Min Act: -0.0001
Data Index: 599110 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.1940. Min Act: -0.0001
Data Index: 1232907 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.1429. Min Act: -0.0001
Data Index: 856462 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.1565. Min Act: -0.0001
Data Index: 1327325 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.1904. Min Act: -0.0001
Data Index: 573389 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.1406. Min Act: -0.0001
Data Index: 985214 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.1098. Min Act: -0.0001
Data Index: 925794 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.1327. Min Act: -0.0001
Data Index: 961715 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.1840. Min Act: -0.0001
Data Index: 679611 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.0839. Min Act: -0.0001
Data Index: 1210691 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2724. Min Range: -1.2724
Max Act: 1.0216. Min Act: -0.0001
Data Index: 1134692 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2724. Min Range: -1.2724
Max Act: 0.9871. Min Act: -0.0001
Data Index: 989226 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2724. Min Range: -1.2724
Max Act: 0.9507. Min Act: -0.0001
Data Index: 1249370 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2724. Min Range: -1.2724
Max Act: 0.9623. Min Act: -0.0001
Data Index: 1055592 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2724. Min Range: -1.2724
Max Act: 0.9173. Min Act: -0.0001
Data Index: 1492094 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2724. Min Range: -1.2724
Max Act: 0.8722. Min Act: -0.0001
Data Index: 889566 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2724. Min Range: -1.2724
Max Act: 0.8684. Min Act: -0.0001
Data Index: 888205 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2724. Min Range: -1.2724
Max Act: 0.8545. Min Act: -0.0001
Data Index: 1291244 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19