Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3187 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.8726. Min Act: -0.0001
Data Index: 277790 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.8419. Min Act: -0.0001
Data Index: 15015 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.8306. Min Act: -0.0001
Data Index: 594347 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.8013. Min Act: -0.0000
Data Index: 112905 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.8326. Min Act: -0.0001
Data Index: 652769 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.7629. Min Act: -0.0001
Data Index: 1351303 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.7422. Min Act: -0.0001
Data Index: 1061210 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.7603. Min Act: -0.0001
Data Index: 580204 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.7333. Min Act: -0.0001
Data Index: 847755 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.6748. Min Act: -0.0001
Data Index: 1157394 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.7417. Min Act: -0.0001
Data Index: 536617 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.7102. Min Act: -0.0001
Data Index: 130057 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.7056. Min Act: -0.0001
Data Index: 79004 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.6633. Min Act: -0.0001
Data Index: 755646 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.7237. Min Act: -0.0001
Data Index: 750426 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.7238. Min Act: -0.0001
Data Index: 38524 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.6497. Min Act: -0.0001
Data Index: 167673 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.6484. Min Act: -0.0001
Data Index: 2704 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.6953. Min Act: -0.0001
Data Index: 131247 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8726. Min Range: -0.8726
Max Act: 0.6898. Min Act: -0.0001
Data Index: 713571 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19