Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2550 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0841. Min Act: -0.0001
Data Index: 40667 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0854. Min Act: -0.0001
Data Index: 908170 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0945. Min Act: -0.0001
Data Index: 1096817 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0883. Min Act: -0.0001
Data Index: 1340100 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0789. Min Act: -0.0001
Data Index: 1337640 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0867. Min Act: -0.0001
Data Index: 280500 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0830. Min Act: -0.0001
Data Index: 548040 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0770. Min Act: -0.0001
Data Index: 961878 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0801. Min Act: -0.0001
Data Index: 532023 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0846. Min Act: -0.0001
Data Index: 1285850 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0699. Min Act: -0.0001
Data Index: 643965 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0746. Min Act: -0.0001
Data Index: 1060210 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0748. Min Act: -0.0001
Data Index: 598038 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0776. Min Act: -0.0001
Data Index: 132391 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0779. Min Act: -0.0001
Data Index: 768283 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0776. Min Act: -0.0001
Data Index: 412909 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0732. Min Act: -0.0001
Data Index: 757306 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0779. Min Act: -0.0001
Data Index: 503773 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0684. Min Act: -0.0001
Data Index: 1064172 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0945. Min Range: -0.0945
Max Act: 0.0631. Min Act: -0.0001
Data Index: 439830 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19