Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2700 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.1026. Min Act: -0.0001
Data Index: 825431 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0898. Min Act: -0.0001
Data Index: 1334973 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0750. Min Act: -0.0001
Data Index: 622867 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0802. Min Act: -0.0001
Data Index: 754485 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0824. Min Act: -0.0001
Data Index: 223075 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0798. Min Act: -0.0001
Data Index: 725578 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0759. Min Act: -0.0001
Data Index: 363021 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0699. Min Act: -0.0001
Data Index: 638827 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0738. Min Act: -0.0001
Data Index: 203506 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0706. Min Act: -0.0001
Data Index: 1311505 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0693. Min Act: -0.0001
Data Index: 1175799 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0670. Min Act: -0.0001
Data Index: 773968 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0696. Min Act: -0.0001
Data Index: 317200 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0690. Min Act: -0.0001
Data Index: 707398 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0659. Min Act: -0.0001
Data Index: 128161 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0680. Min Act: -0.0001
Data Index: 1296776 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0660. Min Act: -0.0001
Data Index: 736187 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0676. Min Act: -0.0001
Data Index: 221804 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0679. Min Act: -0.0001
Data Index: 1656655 (Python Code)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1026. Min Range: -0.1026
Max Act: 0.0660. Min Act: -0.0001
Data Index: 487279 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19