Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5088 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.5986. Min Range: -3.5986
Max Act: 3.5986. Min Act: -0.0000
Data Index: 101181 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.8113. Min Act: -0.0001
Data Index: 462199 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.5100. Min Act: -0.0001
Data Index: 690753 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.4156. Min Act: -0.0001
Data Index: 1176556 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5986. Min Range: -3.5986
Max Act: 1.9754. Min Act: -0.0001
Data Index: 437666 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.3048. Min Act: -0.0001
Data Index: 894508 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.3015. Min Act: -0.0001
Data Index: 108465 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.1353. Min Act: -0.0001
Data Index: 321831 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.2083. Min Act: -0.0001
Data Index: 409775 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.0818. Min Act: -0.0001
Data Index: 219301 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.1422. Min Act: -0.0001
Data Index: 1117183 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.0273. Min Act: -0.0001
Data Index: 1051260 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.0172. Min Act: -0.0001
Data Index: 225115 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.0032. Min Act: -0.0001
Data Index: 326413 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.1056. Min Act: -0.0001
Data Index: 1124436 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.0477. Min Act: -0.0001
Data Index: 981335 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.1012. Min Act: -0.0001
Data Index: 749495 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.0734. Min Act: -0.0001
Data Index: 1070903 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5986. Min Range: -3.5986
Max Act: 2.0622. Min Act: -0.0001
Data Index: 124628 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5986. Min Range: -3.5986
Max Act: 1.9363. Min Act: -0.0001
Data Index: 1110454 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19