Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1784 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.7237. Min Act: -0.0001
Data Index: 449141 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6662. Min Act: -0.0001
Data Index: 397178 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6498. Min Act: -0.0001
Data Index: 1132681 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6316. Min Act: -0.0001
Data Index: 72322 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6451. Min Act: -0.0001
Data Index: 269368 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6175. Min Act: -0.0001
Data Index: 329521 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6009. Min Act: -0.0001
Data Index: 992376 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6550. Min Act: -0.0001
Data Index: 885818 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6214. Min Act: -0.0001
Data Index: 1044961 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6376. Min Act: -0.0001
Data Index: 1261605 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6329. Min Act: -0.0001
Data Index: 190185 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6076. Min Act: -0.0001
Data Index: 481853 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.5820. Min Act: -0.0001
Data Index: 1108824 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.5999. Min Act: -0.0001
Data Index: 951155 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.5792. Min Act: -0.0001
Data Index: 602289 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.5817. Min Act: -0.0001
Data Index: 859981 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.5758. Min Act: -0.0001
Data Index: 683915 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.5731. Min Act: -0.0001
Data Index: 275898 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.5908. Min Act: -0.0001
Data Index: 549092 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7237. Min Range: -0.7237
Max Act: 0.6012. Min Act: -0.0001
Data Index: 883569 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19