Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4870 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.8138. Min Act: -0.0001
Data Index: 752349 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.8139. Min Act: -0.0001
Data Index: 1545673 (Python Code)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.7742. Min Act: -0.0001
Data Index: 569537 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.7482. Min Act: -0.0001
Data Index: 500191 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.7171. Min Act: -0.0001
Data Index: 367919 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.7621. Min Act: -0.0001
Data Index: 839431 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.7772. Min Act: -0.0001
Data Index: 844186 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.6984. Min Act: -0.0001
Data Index: 171198 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.7143. Min Act: -0.0001
Data Index: 986505 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.7008. Min Act: -0.0001
Data Index: 582468 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.7113. Min Act: -0.0001
Data Index: 503558 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.7071. Min Act: -0.0001
Data Index: 299938 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.5937. Min Act: -0.0001
Data Index: 1500933 (Python Code)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.6998. Min Act: -0.0001
Data Index: 47236 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.6267. Min Act: -0.0001
Data Index: 1054505 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.6307. Min Act: -0.0001
Data Index: 863483 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.6056. Min Act: -0.0001
Data Index: 1274479 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.6421. Min Act: -0.0001
Data Index: 167792 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.6516. Min Act: -0.0001
Data Index: 1004004 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8139. Min Range: -0.8139
Max Act: 0.6134. Min Act: -0.0001
Data Index: 405735 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19