Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1856 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.8930. Min Act: -0.0001
Data Index: 19297 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.8982. Min Act: -0.0001
Data Index: 842223 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1413. Min Range: -3.1413
Max Act: 3.1413. Min Act: -0.0001
Data Index: 1280478 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.6169. Min Act: -0.0001
Data Index: 1006635 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.4807. Min Act: -0.0001
Data Index: 834869 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.3281. Min Act: -0.0001
Data Index: 1356654 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.0500. Min Act: -0.0001
Data Index: 899794 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.5574. Min Act: -0.0001
Data Index: 726090 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.3865. Min Act: -0.0001
Data Index: 128229 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.3438. Min Act: -0.0001
Data Index: 480532 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.2762. Min Act: -0.0001
Data Index: 362172 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.2700. Min Act: -0.0001
Data Index: 1278571 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.2781. Min Act: -0.0001
Data Index: 952894 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.2513. Min Act: -0.0001
Data Index: 872254 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.1828. Min Act: -0.0001
Data Index: 301913 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.0112. Min Act: -0.0001
Data Index: 533187 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.1242. Min Act: -0.0001
Data Index: 759287 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.2463. Min Act: -0.0001
Data Index: 222288 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.4978. Min Act: -0.0001
Data Index: 328430 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1413. Min Range: -3.1413
Max Act: 2.0913. Min Act: -0.0001
Data Index: 635109 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19