Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3607 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.9073. Min Range: -3.9073
Max Act: 3.9073. Min Act: -0.0001
Data Index: 1068615 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9073. Min Range: -3.9073
Max Act: 3.1709. Min Act: -0.0001
Data Index: 69796 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9073. Min Range: -3.9073
Max Act: 2.2762. Min Act: -0.0001
Data Index: 321146 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9073. Min Range: -3.9073
Max Act: 2.1295. Min Act: -0.0001
Data Index: 29395 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.9932. Min Act: -0.0001
Data Index: 1106141 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.8834. Min Act: -0.0001
Data Index: 80428 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.7093. Min Act: -0.0001
Data Index: 431378 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.7771. Min Act: -0.0001
Data Index: 44328 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9073. Min Range: -3.9073
Max Act: 2.0055. Min Act: -0.0001
Data Index: 807722 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.7189. Min Act: -0.0001
Data Index: 464654 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.9302. Min Act: -0.0001
Data Index: 312445 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.5386. Min Act: -0.0001
Data Index: 509091 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.5566. Min Act: -0.0001
Data Index: 677712 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.7845. Min Act: -0.0001
Data Index: 134180 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.7724. Min Act: -0.0001
Data Index: 162325 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.5659. Min Act: -0.0001
Data Index: 1064916 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.6564. Min Act: -0.0001
Data Index: 1034786 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.7358. Min Act: -0.0001
Data Index: 392372 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.6544. Min Act: -0.0001
Data Index: 824426 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9073. Min Range: -3.9073
Max Act: 1.4774. Min Act: -0.0001
Data Index: 237879 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19