Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3588 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.6668. Min Act: -0.0001
Data Index: 1459573 (Python Code)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.6048. Min Act: -0.0001
Data Index: 669590 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.5642. Min Act: -0.0001
Data Index: 600463 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.6278. Min Act: -0.0001
Data Index: 815811 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.5414. Min Act: -0.0001
Data Index: 715892 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.5491. Min Act: -0.0001
Data Index: 1348604 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.5656. Min Act: -0.0001
Data Index: 945688 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.5279. Min Act: -0.0001
Data Index: 613232 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.4861. Min Act: -0.0001
Data Index: 984312 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.4576. Min Act: -0.0001
Data Index: 337160 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.5193. Min Act: -0.0001
Data Index: 350799 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.5286. Min Act: -0.0001
Data Index: 666357 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.5109. Min Act: -0.0001
Data Index: 1005797 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.4937. Min Act: -0.0001
Data Index: 344564 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.4953. Min Act: -0.0001
Data Index: 548276 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.4772. Min Act: -0.0001
Data Index: 461940 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.4760. Min Act: -0.0001
Data Index: 255751 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.4914. Min Act: -0.0001
Data Index: 1300660 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.4766. Min Act: -0.0001
Data Index: 85301 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6668. Min Range: -0.6668
Max Act: 0.4973. Min Act: -0.0001
Data Index: 1508111 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19