Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 53 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.9623. Min Act: -0.0001
Data Index: 1319266 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.9149. Min Act: -0.0001
Data Index: 467166 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.8367. Min Act: -0.0001
Data Index: 695820 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.8744. Min Act: -0.0001
Data Index: 342687 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.6806. Min Act: -0.0001
Data Index: 1458754 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.7072. Min Act: -0.0001
Data Index: 266344 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.7466. Min Act: -0.0001
Data Index: 1614603 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.6353. Min Act: -0.0001
Data Index: 1488895 (Python Code)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.6742. Min Act: -0.0001
Data Index: 1350282 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.6744. Min Act: -0.0001
Data Index: 1491429 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.4737. Min Act: -0.0001
Data Index: 1366698 (Python Code)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.6714. Min Act: -0.0001
Data Index: 733816 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.6543. Min Act: -0.0001
Data Index: 1570436 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.5847. Min Act: -0.0001
Data Index: 1375892 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.6478. Min Act: -0.0001
Data Index: 1365018 (Python Code)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.5527. Min Act: -0.0001
Data Index: 858017 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.4081. Min Act: -0.0001
Data Index: 1448792 (Python Code)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.5559. Min Act: -0.0001
Data Index: 43266 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.5948. Min Act: -0.0001
Data Index: 836769 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9623. Min Range: -0.9623
Max Act: 0.5463. Min Act: -0.0001
Data Index: 1032513 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19