Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1580 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.6680. Min Act: -0.0002
Data Index: 215779 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.7587. Min Act: -0.0002
Data Index: 236858 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.3504. Min Act: -0.0002
Data Index: 237440 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.7086. Min Act: -0.0002
Data Index: 1124883 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.4305. Min Act: -0.0002
Data Index: 1178784 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.3167. Min Act: -0.0001
Data Index: 859480 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.1436. Min Act: -0.0002
Data Index: 198419 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.3899. Min Act: -0.0001
Data Index: 441771 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.2537. Min Act: -0.0002
Data Index: 896330 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.0951. Min Act: -0.0001
Data Index: 277321 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.1742. Min Act: -0.0001
Data Index: 60644 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.2781. Min Act: -0.0001
Data Index: 1009651 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.2490. Min Act: -0.0001
Data Index: 858084 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.1524. Min Act: -0.0002
Data Index: 908010 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.2404. Min Act: -0.0001
Data Index: 940307 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.1858. Min Act: -0.0002
Data Index: 426143 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.2565. Min Act: -0.0002
Data Index: 1301633 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.1539. Min Act: -0.0001
Data Index: 467530 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.1443. Min Act: -0.0002
Data Index: 669242 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7587. Min Range: -2.7587
Max Act: 2.0252. Min Act: -0.0002
Data Index: 1311656 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19