Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4032 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0678. Min Act: -0.0001
Data Index: 134626 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0635. Min Act: -0.0001
Data Index: 1248126 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0646. Min Act: -0.0001
Data Index: 1139875 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0573. Min Act: -0.0001
Data Index: 682920 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0639. Min Act: -0.0001
Data Index: 743800 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0606. Min Act: -0.0001
Data Index: 746623 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0573. Min Act: -0.0001
Data Index: 353379 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0571. Min Act: -0.0001
Data Index: 973442 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0540. Min Act: -0.0001
Data Index: 64251 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0545. Min Act: -0.0001
Data Index: 25684 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0530. Min Act: -0.0001
Data Index: 1294691 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0565. Min Act: -0.0001
Data Index: 182713 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0537. Min Act: -0.0001
Data Index: 345686 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0535. Min Act: -0.0001
Data Index: 308045 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0493. Min Act: -0.0001
Data Index: 355358 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0533. Min Act: -0.0001
Data Index: 84925 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0531. Min Act: -0.0001
Data Index: 642667 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0519. Min Act: -0.0001
Data Index: 143671 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0529. Min Act: -0.0001
Data Index: 722526 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0678. Min Range: -0.0678
Max Act: 0.0551. Min Act: -0.0001
Data Index: 390007 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19