Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1087 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0849. Min Act: -0.0001
Data Index: 833555 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0708. Min Act: -0.0001
Data Index: 412986 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0677. Min Act: -0.0001
Data Index: 735006 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0616. Min Act: -0.0001
Data Index: 1544725 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0617. Min Act: -0.0001
Data Index: 1478608 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0597. Min Act: -0.0001
Data Index: 1176 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0595. Min Act: -0.0001
Data Index: 1652322 (Python Code)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0570. Min Act: -0.0001
Data Index: 1428507 (Python Code)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0585. Min Act: -0.0001
Data Index: 1089530 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0541. Min Act: -0.0001
Data Index: 1436733 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0566. Min Act: -0.0001
Data Index: 1281407 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0545. Min Act: -0.0001
Data Index: 1442863 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0557. Min Act: -0.0001
Data Index: 857693 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0554. Min Act: -0.0001
Data Index: 315338 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0522. Min Act: -0.0001
Data Index: 1532318 (Python Code)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0581. Min Act: -0.0001
Data Index: 1402124 (Python Code)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0490. Min Act: -0.0001
Data Index: 1568526 (Python Code)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0558. Min Act: -0.0001
Data Index: 1523775 (Python Code)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0533. Min Act: -0.0001
Data Index: 523006 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0849. Min Range: -0.0849
Max Act: 0.0478. Min Act: -0.0001
Data Index: 17460 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19