Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3024 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.5402. Min Act: -0.0001
Data Index: 194207 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.5413. Min Act: -0.0001
Data Index: 857172 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.5246. Min Act: -0.0001
Data Index: 136121 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4794. Min Act: -0.0001
Data Index: 1288703 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.5116. Min Act: -0.0001
Data Index: 1097988 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4610. Min Act: -0.0001
Data Index: 706028 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4904. Min Act: -0.0001
Data Index: 962029 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4489. Min Act: -0.0001
Data Index: 1250656 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4801. Min Act: -0.0001
Data Index: 1156004 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4820. Min Act: -0.0001
Data Index: 286181 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4892. Min Act: -0.0001
Data Index: 1156607 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4716. Min Act: -0.0001
Data Index: 1257251 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4883. Min Act: -0.0001
Data Index: 106483 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4434. Min Act: -0.0001
Data Index: 615930 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4684. Min Act: -0.0001
Data Index: 643013 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4484. Min Act: -0.0001
Data Index: 502785 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4505. Min Act: -0.0001
Data Index: 1253506 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4346. Min Act: -0.0001
Data Index: 362132 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4592. Min Act: -0.0001
Data Index: 664613 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5413. Min Range: -0.5413
Max Act: 0.4422. Min Act: -0.0001
Data Index: 622797 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19