Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3256 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.6851. Min Act: -0.0001
Data Index: 174611 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.3772. Min Act: -0.0001
Data Index: 884126 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.3523. Min Act: -0.0001
Data Index: 1291852 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.2994. Min Act: -0.0001
Data Index: 347140 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.0382. Min Act: -0.0001
Data Index: 775653 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.2690. Min Act: -0.0001
Data Index: 76252 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.2668. Min Act: -0.0001
Data Index: 597825 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.2517. Min Act: -0.0001
Data Index: 939241 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.2398. Min Act: -0.0001
Data Index: 336827 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.2301. Min Act: -0.0001
Data Index: 806116 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.0748. Min Act: -0.0001
Data Index: 810838 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6851. Min Range: -2.6851
Max Act: 1.9967. Min Act: -0.0001
Data Index: 646144 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.0464. Min Act: -0.0001
Data Index: 1119102 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.2728. Min Act: -0.0001
Data Index: 1113740 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.1533. Min Act: -0.0001
Data Index: 579295 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.2396. Min Act: -0.0001
Data Index: 701166 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.1522. Min Act: -0.0001
Data Index: 741589 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.1342. Min Act: -0.0001
Data Index: 648440 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.1282. Min Act: -0.0001
Data Index: 725521 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6851. Min Range: -2.6851
Max Act: 2.1283. Min Act: -0.0001
Data Index: 1344645 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19