Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 23 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6655. Min Range: -2.6655
Max Act: 2.6655. Min Act: -0.0001
Data Index: 426817 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.7519. Min Act: -0.0001
Data Index: 785235 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6655. Min Range: -2.6655
Max Act: 2.0053. Min Act: -0.0001
Data Index: 133514 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6655. Min Range: -2.6655
Max Act: 2.0089. Min Act: -0.0001
Data Index: 254475 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.8720. Min Act: -0.0001
Data Index: 1013582 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.7575. Min Act: -0.0001
Data Index: 460227 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.6386. Min Act: -0.0001
Data Index: 32074 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.7246. Min Act: -0.0001
Data Index: 525478 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.8086. Min Act: -0.0001
Data Index: 1118437 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.7559. Min Act: -0.0001
Data Index: 904733 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.6206. Min Act: -0.0001
Data Index: 120889 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.6733. Min Act: -0.0001
Data Index: 47580 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.7833. Min Act: -0.0001
Data Index: 1132099 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.6412. Min Act: -0.0001
Data Index: 670884 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.6373. Min Act: -0.0001
Data Index: 153778 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.7377. Min Act: -0.0001
Data Index: 107490 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.6382. Min Act: -0.0001
Data Index: 540205 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.5385. Min Act: -0.0001
Data Index: 1125636 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.5891. Min Act: -0.0001
Data Index: 391169 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6655. Min Range: -2.6655
Max Act: 1.4575. Min Act: -0.0001
Data Index: 1200038 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19