Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3913 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3191. Min Range: -2.3191
Max Act: 2.3191. Min Act: -0.0001
Data Index: 534590 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.9445. Min Act: -0.0001
Data Index: 640794 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.9415. Min Act: -0.0001
Data Index: 128064 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.7173. Min Act: -0.0001
Data Index: 174982 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.9013. Min Act: -0.0001
Data Index: 1182639 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.4930. Min Act: -0.0001
Data Index: 87954 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.4097. Min Act: -0.0001
Data Index: 561882 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.8167. Min Act: -0.0001
Data Index: 735061 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.7059. Min Act: -0.0001
Data Index: 835296 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.7951. Min Act: -0.0001
Data Index: 982743 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.6108. Min Act: -0.0001
Data Index: 441746 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.5582. Min Act: -0.0001
Data Index: 53864 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.8860. Min Act: -0.0001
Data Index: 1202975 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.6937. Min Act: -0.0001
Data Index: 343869 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.5999. Min Act: -0.0001
Data Index: 124171 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.9297. Min Act: -0.0001
Data Index: 848740 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.8059. Min Act: -0.0001
Data Index: 1299341 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.9912. Min Act: -0.0001
Data Index: 491469 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.7803. Min Act: -0.0001
Data Index: 996130 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3191. Min Range: -2.3191
Max Act: 1.6383. Min Act: -0.0001
Data Index: 1267811 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19