Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1319 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.8523. Min Act: -0.0001
Data Index: 385568 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.7354. Min Act: -0.0001
Data Index: 270868 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.7325. Min Act: -0.0001
Data Index: 1086590 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6634. Min Act: -0.0001
Data Index: 1357783 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6489. Min Act: -0.0001
Data Index: 771219 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6508. Min Act: -0.0001
Data Index: 994667 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6226. Min Act: -0.0001
Data Index: 659037 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6691. Min Act: -0.0001
Data Index: 887263 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6435. Min Act: -0.0001
Data Index: 660392 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.5909. Min Act: -0.0001
Data Index: 416952 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6028. Min Act: -0.0001
Data Index: 1289226 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.5775. Min Act: -0.0001
Data Index: 776338 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6192. Min Act: -0.0001
Data Index: 422759 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.5756. Min Act: -0.0001
Data Index: 351833 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6137. Min Act: -0.0001
Data Index: 899297 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6580. Min Act: -0.0001
Data Index: 968022 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.5836. Min Act: -0.0001
Data Index: 890196 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.5838. Min Act: -0.0001
Data Index: 783905 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.6022. Min Act: -0.0001
Data Index: 925206 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8523. Min Range: -0.8523
Max Act: 0.5640. Min Act: -0.0001
Data Index: 1093010 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19