Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2592 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.3420. Min Act: -0.0001
Data Index: 986037 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.4476. Min Act: -0.0001
Data Index: 28237 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.5672. Min Act: -0.0001
Data Index: 1166471 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.5689. Min Act: -0.0001
Data Index: 284486 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.6647. Min Act: -0.0001
Data Index: 847431 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.4214. Min Act: -0.0001
Data Index: 400038 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.4072. Min Act: -0.0001
Data Index: 426135 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.5832. Min Act: -0.0001
Data Index: 1116572 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.4754. Min Act: -0.0001
Data Index: 1140831 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.4916. Min Act: -0.0001
Data Index: 850636 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.2063. Min Act: -0.0001
Data Index: 389984 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.4628. Min Act: -0.0001
Data Index: 428675 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.6912. Min Act: -0.0001
Data Index: 353135 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.4374. Min Act: -0.0001
Data Index: 353140 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.5667. Min Act: -0.0001
Data Index: 664279 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.3115. Min Act: -0.0001
Data Index: 1299797 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.4042. Min Act: -0.0001
Data Index: 240561 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.5179. Min Act: -0.0001
Data Index: 1172764 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.2843. Min Act: -0.0001
Data Index: 1172559 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6912. Min Range: -2.6912
Max Act: 2.1297. Min Act: -0.0001
Data Index: 234131 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19