Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2806 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0763. Min Act: -0.0001
Data Index: 990971 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0685. Min Act: -0.0001
Data Index: 27470 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0668. Min Act: -0.0001
Data Index: 970979 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0610. Min Act: -0.0001
Data Index: 536972 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0613. Min Act: -0.0001
Data Index: 114757 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0550. Min Act: -0.0001
Data Index: 1130447 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0515. Min Act: -0.0001
Data Index: 296589 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0512. Min Act: -0.0001
Data Index: 304529 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0509. Min Act: -0.0001
Data Index: 1225605 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0516. Min Act: -0.0001
Data Index: 1253276 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0524. Min Act: -0.0001
Data Index: 243979 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0554. Min Act: -0.0001
Data Index: 385947 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0498. Min Act: -0.0001
Data Index: 457864 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0478. Min Act: -0.0001
Data Index: 839547 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0515. Min Act: -0.0001
Data Index: 1243164 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0520. Min Act: -0.0001
Data Index: 1215304 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0508. Min Act: -0.0001
Data Index: 853217 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0471. Min Act: -0.0001
Data Index: 504608 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0528. Min Act: -0.0001
Data Index: 596294 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0763. Min Range: -0.0763
Max Act: 0.0511. Min Act: -0.0001
Data Index: 241688 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19