Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3222 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.9260. Min Act: -0.0001
Data Index: 978145 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.3769. Min Act: -0.0001
Data Index: 396891 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.7529. Min Act: -0.0001
Data Index: 65500 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.3281. Min Act: -0.0001
Data Index: 852454 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.4454. Min Act: -0.0001
Data Index: 1351817 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.4040. Min Act: -0.0001
Data Index: 832473 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.1675. Min Act: -0.0001
Data Index: 960673 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.1968. Min Act: -0.0001
Data Index: 975574 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.1840. Min Act: -0.0001
Data Index: 547829 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.2247. Min Act: -0.0001
Data Index: 327677 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.2749. Min Act: -0.0001
Data Index: 10468 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.2387. Min Act: -0.0001
Data Index: 46753 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9260. Min Range: -1.9260
Max Act: 0.9317. Min Act: -0.0001
Data Index: 659867 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.1061. Min Act: -0.0001
Data Index: 250218 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.1267. Min Act: -0.0001
Data Index: 1125624 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.1286. Min Act: -0.0001
Data Index: 454442 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.1033. Min Act: -0.0001
Data Index: 1106878 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.1149. Min Act: -0.0001
Data Index: 1127501 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.1356. Min Act: -0.0001
Data Index: 1174055 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9260. Min Range: -1.9260
Max Act: 1.0615. Min Act: -0.0001
Data Index: 551720 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19