Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2800 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.8014. Min Act: -0.0001
Data Index: 1089105 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.7115. Min Act: -0.0001
Data Index: 207915 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.6659. Min Act: -0.0001
Data Index: 914833 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.3414. Min Act: -0.0000
Data Index: 399355 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.4241. Min Act: -0.0001
Data Index: 497279 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.1301. Min Act: -0.0001
Data Index: 1338745 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.2631. Min Act: -0.0000
Data Index: 962193 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.2402. Min Act: -0.0001
Data Index: 116596 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.0332. Min Act: -0.0001
Data Index: 913700 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.1973. Min Act: -0.0000
Data Index: 1080976 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.0635. Min Act: -0.0001
Data Index: 1020240 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.1538. Min Act: -0.0001
Data Index: 932977 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8014. Min Range: -2.8014
Max Act: 1.8966. Min Act: -0.0001
Data Index: 738124 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8014. Min Range: -2.8014
Max Act: 1.9895. Min Act: -0.0001
Data Index: 801825 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.0023. Min Act: -0.0001
Data Index: 1175446 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.1888. Min Act: -0.0001
Data Index: 1104598 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.2937. Min Act: -0.0001
Data Index: 321154 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.0536. Min Act: -0.0001
Data Index: 1303835 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.0418. Min Act: -0.0001
Data Index: 220115 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8014. Min Range: -2.8014
Max Act: 2.0131. Min Act: -0.0001
Data Index: 676763 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19