Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4770 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.2505. Min Range: -4.2505
Max Act: 4.2505. Min Act: -0.0001
Data Index: 700016 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2505. Min Range: -4.2505
Max Act: 4.0803. Min Act: -0.0001
Data Index: 813743 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.7460. Min Act: -0.0001
Data Index: 1316850 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.6074. Min Act: -0.0001
Data Index: 1275535 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.3548. Min Act: -0.0001
Data Index: 1284348 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.1843. Min Act: -0.0001
Data Index: 1309602 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.6034. Min Act: -0.0001
Data Index: 691990 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.4332. Min Act: -0.0001
Data Index: 573030 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.1562. Min Act: -0.0001
Data Index: 113735 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2505. Min Range: -4.2505
Max Act: 2.9482. Min Act: -0.0001
Data Index: 489558 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.3028. Min Act: -0.0001
Data Index: 1224971 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2505. Min Range: -4.2505
Max Act: 2.7496. Min Act: -0.0001
Data Index: 443232 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.1274. Min Act: -0.0001
Data Index: 859370 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2505. Min Range: -4.2505
Max Act: 2.8214. Min Act: -0.0001
Data Index: 772652 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.4003. Min Act: -0.0001
Data Index: 1149452 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.0461. Min Act: -0.0001
Data Index: 485154 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.1597. Min Act: -0.0001
Data Index: 403367 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.1588. Min Act: -0.0001
Data Index: 114392 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.3507. Min Act: -0.0001
Data Index: 818796 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2505. Min Range: -4.2505
Max Act: 3.1500. Min Act: -0.0001
Data Index: 471848 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19