Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2981 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.8802. Min Act: -0.0001
Data Index: 989410 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.6468. Min Act: -0.0001
Data Index: 710476 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.5755. Min Act: -0.0001
Data Index: 697733 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.5238. Min Act: -0.0001
Data Index: 343379 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.4833. Min Act: -0.0001
Data Index: 1090051 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.5931. Min Act: -0.0001
Data Index: 34946 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.5189. Min Act: -0.0001
Data Index: 1099799 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.3321. Min Act: -0.0001
Data Index: 956263 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.3932. Min Act: -0.0001
Data Index: 662049 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.3851. Min Act: -0.0001
Data Index: 146281 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.3776. Min Act: -0.0001
Data Index: 178238 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.2896. Min Act: -0.0001
Data Index: 8806 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.3705. Min Act: -0.0001
Data Index: 202483 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.2623. Min Act: -0.0001
Data Index: 825229 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.3406. Min Act: -0.0001
Data Index: 842030 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.4229. Min Act: -0.0001
Data Index: 43991 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.3245. Min Act: -0.0001
Data Index: 541275 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.4017. Min Act: -0.0001
Data Index: 1131614 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.2466. Min Act: -0.0001
Data Index: 725672 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8802. Min Range: -1.8802
Max Act: 1.2823. Min Act: -0.0001
Data Index: 1093956 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19