Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3232 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.7332. Min Act: -0.0001
Data Index: 536173 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5970. Min Act: -0.0001
Data Index: 496349 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5933. Min Act: -0.0001
Data Index: 370499 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5856. Min Act: -0.0001
Data Index: 152104 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.6059. Min Act: -0.0001
Data Index: 290133 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5681. Min Act: -0.0001
Data Index: 189196 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5819. Min Act: -0.0001
Data Index: 132390 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5626. Min Act: -0.0001
Data Index: 988700 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5925. Min Act: -0.0001
Data Index: 200761 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5839. Min Act: -0.0001
Data Index: 312010 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5500. Min Act: -0.0001
Data Index: 140644 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5652. Min Act: -0.0001
Data Index: 1277317 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.4961. Min Act: -0.0001
Data Index: 715648 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5417. Min Act: -0.0001
Data Index: 217699 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5414. Min Act: -0.0001
Data Index: 1307507 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5798. Min Act: -0.0001
Data Index: 733660 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5256. Min Act: -0.0001
Data Index: 673777 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.5038. Min Act: -0.0001
Data Index: 399980 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.4681. Min Act: -0.0001
Data Index: 405584 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7332. Min Range: -0.7332
Max Act: 0.4998. Min Act: -0.0001
Data Index: 659479 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19