Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3563 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.4034. Min Range: -2.4034
Max Act: 2.4034. Min Act: -0.0001
Data Index: 6066 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4034. Min Range: -2.4034
Max Act: 2.2571. Min Act: -0.0001
Data Index: 1135087 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4034. Min Range: -2.4034
Max Act: 2.1214. Min Act: -0.0001
Data Index: 561745 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4034. Min Range: -2.4034
Max Act: 2.1666. Min Act: -0.0001
Data Index: 1291035 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.9627. Min Act: -0.0001
Data Index: 1236268 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.8175. Min Act: -0.0001
Data Index: 199851 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.8125. Min Act: -0.0001
Data Index: 903179 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.7733. Min Act: -0.0001
Data Index: 349214 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.7225. Min Act: -0.0001
Data Index: 1242288 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.6772. Min Act: -0.0001
Data Index: 25979 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.6385. Min Act: -0.0001
Data Index: 249111 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.6299. Min Act: -0.0001
Data Index: 337841 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.4888. Min Act: -0.0001
Data Index: 1316019 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.6155. Min Act: -0.0001
Data Index: 668215 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.6109. Min Act: -0.0001
Data Index: 112376 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.5391. Min Act: -0.0001
Data Index: 878499 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.5838. Min Act: -0.0001
Data Index: 412031 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.5767. Min Act: -0.0001
Data Index: 762536 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.5680. Min Act: -0.0001
Data Index: 848901 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4034. Min Range: -2.4034
Max Act: 1.5571. Min Act: -0.0001
Data Index: 131598 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19