Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5095 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.5984. Min Act: -0.0001
Data Index: 1292494 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.1726. Min Act: -0.0001
Data Index: 697208 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.3300. Min Act: -0.0001
Data Index: 1218974 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.2900. Min Act: -0.0001
Data Index: 846528 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.1821. Min Act: -0.0001
Data Index: 73047 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5984. Min Range: -4.5984
Max Act: 3.9777. Min Act: -0.0001
Data Index: 830359 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5984. Min Range: -4.5984
Max Act: 3.9717. Min Act: -0.0001
Data Index: 1035951 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5984. Min Range: -4.5984
Max Act: 3.7327. Min Act: -0.0001
Data Index: 463449 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.0392. Min Act: -0.0001
Data Index: 796221 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.0282. Min Act: -0.0001
Data Index: 92137 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.2039. Min Act: -0.0001
Data Index: 1113820 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.0100. Min Act: -0.0001
Data Index: 677735 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.0062. Min Act: -0.0001
Data Index: 1292675 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5984. Min Range: -4.5984
Max Act: 3.8084. Min Act: -0.0001
Data Index: 23309 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5984. Min Range: -4.5984
Max Act: 3.9776. Min Act: -0.0001
Data Index: 991895 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5984. Min Range: -4.5984
Max Act: 4.1150. Min Act: -0.0001
Data Index: 1048351 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5984. Min Range: -4.5984
Max Act: 3.7890. Min Act: -0.0001
Data Index: 75036 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5984. Min Range: -4.5984
Max Act: 3.6141. Min Act: -0.0001
Data Index: 60193 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5984. Min Range: -4.5984
Max Act: 3.9448. Min Act: -0.0001
Data Index: 252397 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5984. Min Range: -4.5984
Max Act: 3.9207. Min Act: -0.0001
Data Index: 506857 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19