Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 101 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.8688. Min Act: -0.0001
Data Index: 372054 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.8624. Min Act: -0.0001
Data Index: 365737 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.7576. Min Act: -0.0001
Data Index: 698257 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6521. Min Act: -0.0001
Data Index: 1425312 (Python Code)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6485. Min Act: -0.0001
Data Index: 318835 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.7224. Min Act: -0.0001
Data Index: 260910 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6173. Min Act: -0.0001
Data Index: 176662 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6693. Min Act: -0.0001
Data Index: 541959 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6856. Min Act: -0.0001
Data Index: 1493973 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6137. Min Act: -0.0001
Data Index: 1185294 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6138. Min Act: -0.0001
Data Index: 1357769 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6220. Min Act: -0.0001
Data Index: 360505 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6449. Min Act: -0.0001
Data Index: 870601 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6021. Min Act: -0.0001
Data Index: 1352392 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6007. Min Act: -0.0001
Data Index: 15564 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6316. Min Act: -0.0001
Data Index: 227030 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6945. Min Act: -0.0001
Data Index: 1355400 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6290. Min Act: -0.0001
Data Index: 369596 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6265. Min Act: -0.0001
Data Index: 1541995 (Python Code)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8688. Min Range: -0.8688
Max Act: 0.6574. Min Act: -0.0001
Data Index: 1592658 (Python Code)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19