Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2702 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.6696. Min Act: -0.0001
Data Index: 70184 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.4361. Min Act: -0.0001
Data Index: 999375 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.3339. Min Act: -0.0001
Data Index: 1138600 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.2942. Min Act: -0.0001
Data Index: 822799 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.4391. Min Act: -0.0001
Data Index: 774056 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.0789. Min Act: -0.0001
Data Index: 1183084 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.2674. Min Act: -0.0001
Data Index: 60669 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.2197. Min Act: -0.0001
Data Index: 1243939 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1132. Min Act: -0.0001
Data Index: 163037 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1347. Min Act: -0.0001
Data Index: 968916 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1604. Min Act: -0.0001
Data Index: 634497 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1990. Min Act: -0.0001
Data Index: 278584 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.2729. Min Act: -0.0001
Data Index: 510658 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.2255. Min Act: -0.0001
Data Index: 435977 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1743. Min Act: -0.0001
Data Index: 402706 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1800. Min Act: -0.0001
Data Index: 805771 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1256. Min Act: -0.0001
Data Index: 699747 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1554. Min Act: -0.0001
Data Index: 692993 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1805. Min Act: -0.0001
Data Index: 1188183 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6696. Min Range: -1.6696
Max Act: 1.1877. Min Act: -0.0001
Data Index: 26927 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19