Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1889 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.9404. Min Act: -0.0001
Data Index: 549767 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.8074. Min Act: -0.0001
Data Index: 67844 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.8162. Min Act: -0.0001
Data Index: 320120 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7635. Min Act: -0.0001
Data Index: 489777 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7162. Min Act: -0.0001
Data Index: 552183 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7538. Min Act: -0.0001
Data Index: 1146798 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7506. Min Act: -0.0001
Data Index: 670877 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7675. Min Act: -0.0001
Data Index: 1124060 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7876. Min Act: -0.0001
Data Index: 766923 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7408. Min Act: -0.0001
Data Index: 165712 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7824. Min Act: -0.0001
Data Index: 358633 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7578. Min Act: -0.0001
Data Index: 1514262 (Python Code)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7618. Min Act: -0.0001
Data Index: 1396366 (Python Code)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7364. Min Act: -0.0001
Data Index: 223809 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7743. Min Act: -0.0001
Data Index: 908464 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7308. Min Act: -0.0001
Data Index: 119281 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7071. Min Act: -0.0001
Data Index: 522743 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.7138. Min Act: -0.0001
Data Index: 587748 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.6888. Min Act: -0.0001
Data Index: 109363 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9404. Min Range: -0.9404
Max Act: 0.6914. Min Act: -0.0001
Data Index: 201081 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19