Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3422 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.7921. Min Act: -0.0001
Data Index: 256016 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.7262. Min Act: -0.0001
Data Index: 1137655 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6858. Min Act: -0.0001
Data Index: 1358428 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.7021. Min Act: -0.0001
Data Index: 1496950 (Python Code)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6717. Min Act: -0.0001
Data Index: 484146 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.7031. Min Act: -0.0001
Data Index: 493551 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6618. Min Act: -0.0001
Data Index: 38776 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6776. Min Act: -0.0001
Data Index: 918459 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6725. Min Act: -0.0001
Data Index: 889925 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6752. Min Act: -0.0001
Data Index: 1168432 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6900. Min Act: -0.0001
Data Index: 1399773 (Python Code)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6356. Min Act: -0.0001
Data Index: 147510 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6547. Min Act: -0.0001
Data Index: 1122156 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6359. Min Act: -0.0001
Data Index: 482808 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6423. Min Act: -0.0001
Data Index: 118150 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6454. Min Act: -0.0001
Data Index: 370573 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6418. Min Act: -0.0001
Data Index: 1257041 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6233. Min Act: -0.0001
Data Index: 1241783 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6354. Min Act: -0.0001
Data Index: 345582 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7921. Min Range: -0.7921
Max Act: 0.6353. Min Act: -0.0001
Data Index: 1160390 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19