Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3197 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.3597. Min Act: -0.0001
Data Index: 110617 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2142. Min Act: -0.0001
Data Index: 1541758 (Python Code)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1920. Min Act: -0.0001
Data Index: 1218352 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.0649. Min Act: -0.0001
Data Index: 1516649 (Python Code)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2427. Min Act: -0.0001
Data Index: 1589889 (Python Code)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3597. Min Range: -1.3597
Max Act: 0.9875. Min Act: -0.0001
Data Index: 1609051 (Python Code)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1642. Min Act: -0.0001
Data Index: 1423621 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1577. Min Act: -0.0001
Data Index: 1462196 (Python Code)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.0631. Min Act: -0.0002
Data Index: 1548214 (Python Code)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1335. Min Act: -0.0001
Data Index: 210519 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2475. Min Act: -0.0001
Data Index: 1546412 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2484. Min Act: -0.0001
Data Index: 1599117 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.0955. Min Act: -0.0001
Data Index: 299407 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.0884. Min Act: -0.0001
Data Index: 1647663 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1727. Min Act: -0.0001
Data Index: 268405 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3597. Min Range: -1.3597
Max Act: 0.9935. Min Act: -0.0001
Data Index: 1241010 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.0245. Min Act: -0.0001
Data Index: 86448 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1036. Min Act: -0.0001
Data Index: 705205 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.0172. Min Act: -0.0001
Data Index: 1498546 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1028. Min Act: -0.0001
Data Index: 687681 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19