Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2015 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1721. Min Act: -0.0001
Data Index: 1063704 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1759. Min Act: -0.0001
Data Index: 1099582 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1561. Min Act: -0.0001
Data Index: 1317327 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1478. Min Act: -0.0001
Data Index: 849161 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1428. Min Act: -0.0001
Data Index: 34398 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1483. Min Act: -0.0001
Data Index: 844185 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1380. Min Act: -0.0001
Data Index: 358147 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1420. Min Act: -0.0001
Data Index: 788689 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1491. Min Act: -0.0001
Data Index: 1250720 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1488. Min Act: -0.0001
Data Index: 1197922 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1338. Min Act: -0.0001
Data Index: 484431 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1444. Min Act: -0.0001
Data Index: 134958 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1342. Min Act: -0.0001
Data Index: 1132224 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1420. Min Act: -0.0001
Data Index: 1358528 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1465. Min Act: -0.0001
Data Index: 196051 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1403. Min Act: -0.0001
Data Index: 428791 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1348. Min Act: -0.0001
Data Index: 228353 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1336. Min Act: -0.0001
Data Index: 252971 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1327. Min Act: -0.0001
Data Index: 135665 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1759. Min Range: -0.1759
Max Act: 0.1380. Min Act: -0.0001
Data Index: 1075480 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19