Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2581 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0821. Min Act: -0.0001
Data Index: 1051334 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0823. Min Act: -0.0001
Data Index: 143978 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0756. Min Act: -0.0001
Data Index: 784171 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0775. Min Act: -0.0001
Data Index: 501734 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0768. Min Act: -0.0001
Data Index: 783487 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0790. Min Act: -0.0001
Data Index: 496804 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0703. Min Act: -0.0001
Data Index: 706056 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0709. Min Act: -0.0001
Data Index: 815683 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0684. Min Act: -0.0001
Data Index: 90345 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0696. Min Act: -0.0001
Data Index: 328457 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0755. Min Act: -0.0001
Data Index: 1121946 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0714. Min Act: -0.0001
Data Index: 992964 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0663. Min Act: -0.0001
Data Index: 957135 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0653. Min Act: -0.0001
Data Index: 804568 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0668. Min Act: -0.0001
Data Index: 102250 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0642. Min Act: -0.0001
Data Index: 1111129 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0643. Min Act: -0.0001
Data Index: 1129624 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0640. Min Act: -0.0001
Data Index: 54217 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0671. Min Act: -0.0001
Data Index: 296451 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0823. Min Range: -0.0823
Max Act: 0.0620. Min Act: -0.0001
Data Index: 521413 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19