Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6095 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.2932. Min Act: -0.0001
Data Index: 561221 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.2236. Min Act: -0.0001
Data Index: 369720 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0992. Min Act: -0.0001
Data Index: 742803 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.1087. Min Act: -0.0001
Data Index: 84064 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0533. Min Act: -0.0001
Data Index: 292019 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0854. Min Act: -0.0001
Data Index: 262553 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0435. Min Act: -0.0001
Data Index: 945047 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0596. Min Act: -0.0001
Data Index: 761818 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.1028. Min Act: -0.0001
Data Index: 463451 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0644. Min Act: -0.0001
Data Index: 594122 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0746. Min Act: -0.0001
Data Index: 463666 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0545. Min Act: -0.0001
Data Index: 973994 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2932. Min Range: -1.2932
Max Act: 0.9543. Min Act: -0.0001
Data Index: 600042 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2932. Min Range: -1.2932
Max Act: 0.9762. Min Act: -0.0001
Data Index: 908570 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0058. Min Act: -0.0001
Data Index: 1239431 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0075. Min Act: -0.0001
Data Index: 1066219 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2932. Min Range: -1.2932
Max Act: 0.9383. Min Act: -0.0001
Data Index: 24079 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2932. Min Range: -1.2932
Max Act: 1.0279. Min Act: -0.0001
Data Index: 1108297 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2932. Min Range: -1.2932
Max Act: 0.9920. Min Act: -0.0001
Data Index: 120817 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2932. Min Range: -1.2932
Max Act: 0.9885. Min Act: -0.0001
Data Index: 1305810 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19