Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5426 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5554. Min Range: -2.5554
Max Act: 2.5554. Min Act: -0.0000
Data Index: 1241978 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5554. Min Range: -2.5554
Max Act: 2.2480. Min Act: -0.0000
Data Index: 468082 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5554. Min Range: -2.5554
Max Act: 2.4493. Min Act: -0.0000
Data Index: 42785 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5554. Min Range: -2.5554
Max Act: 2.2595. Min Act: -0.0001
Data Index: 23969 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5554. Min Range: -2.5554
Max Act: 2.3781. Min Act: -0.0000
Data Index: 216157 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.7773. Min Act: -0.0000
Data Index: 560251 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.8397. Min Act: -0.0001
Data Index: 543325 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5554. Min Range: -2.5554
Max Act: 2.0671. Min Act: -0.0001
Data Index: 827731 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.8437. Min Act: -0.0001
Data Index: 1050611 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.9219. Min Act: -0.0000
Data Index: 349777 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5554. Min Range: -2.5554
Max Act: 2.0978. Min Act: -0.0000
Data Index: 1147029 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.9414. Min Act: -0.0001
Data Index: 415313 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.8965. Min Act: -0.0001
Data Index: 960221 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5554. Min Range: -2.5554
Max Act: 2.1069. Min Act: -0.0001
Data Index: 1103567 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.7613. Min Act: -0.0001
Data Index: 143667 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.9537. Min Act: -0.0001
Data Index: 30872 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.9209. Min Act: -0.0001
Data Index: 443037 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.9310. Min Act: -0.0000
Data Index: 1304892 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.8011. Min Act: -0.0000
Data Index: 159469 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5554. Min Range: -2.5554
Max Act: 1.7713. Min Act: -0.0001
Data Index: 704923 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19