Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 258 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0782. Min Act: -0.0001
Data Index: 376162 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0762. Min Act: -0.0001
Data Index: 407920 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0745. Min Act: -0.0001
Data Index: 1063509 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0686. Min Act: -0.0001
Data Index: 973511 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0686. Min Act: -0.0001
Data Index: 1018249 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0721. Min Act: -0.0001
Data Index: 719901 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0682. Min Act: -0.0001
Data Index: 1418922 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0674. Min Act: -0.0001
Data Index: 497897 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0628. Min Act: -0.0001
Data Index: 1101576 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0627. Min Act: -0.0001
Data Index: 1091490 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0664. Min Act: -0.0001
Data Index: 1594028 (Python Code)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0659. Min Act: -0.0001
Data Index: 1167566 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0655. Min Act: -0.0001
Data Index: 793272 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0642. Min Act: -0.0001
Data Index: 274041 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0641. Min Act: -0.0001
Data Index: 663266 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0631. Min Act: -0.0001
Data Index: 925797 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0602. Min Act: -0.0001
Data Index: 25032 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0623. Min Act: -0.0001
Data Index: 1283947 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0591. Min Act: -0.0001
Data Index: 792289 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0782. Min Range: -0.0782
Max Act: 0.0635. Min Act: -0.0001
Data Index: 1054461 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19