Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 971 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.8290. Min Act: -0.0001
Data Index: 899968 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.7245. Min Act: -0.0001
Data Index: 450359 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6256. Min Act: -0.0001
Data Index: 1154046 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6803. Min Act: -0.0001
Data Index: 942946 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6537. Min Act: -0.0001
Data Index: 1035501 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6691. Min Act: -0.0001
Data Index: 289707 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6256. Min Act: -0.0001
Data Index: 474141 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6219. Min Act: -0.0001
Data Index: 598064 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6161. Min Act: -0.0001
Data Index: 1123712 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6338. Min Act: -0.0001
Data Index: 762638 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6091. Min Act: -0.0001
Data Index: 707439 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.5621. Min Act: -0.0001
Data Index: 1298241 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.7083. Min Act: -0.0001
Data Index: 1172882 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.5839. Min Act: -0.0001
Data Index: 601033 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.5605. Min Act: -0.0001
Data Index: 1310524 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.5893. Min Act: -0.0001
Data Index: 455673 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.5534. Min Act: -0.0001
Data Index: 14841 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.5503. Min Act: -0.0001
Data Index: 1337816 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.5496. Min Act: -0.0001
Data Index: 1134351 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8290. Min Range: -0.8290
Max Act: 0.6112. Min Act: -0.0001
Data Index: 678630 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19