Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3056 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.1709. Min Act: -0.0001
Data Index: 159574 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.2103. Min Act: -0.0001
Data Index: 52751 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.1275. Min Act: -0.0001
Data Index: 1255724 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.1058. Min Act: -0.0001
Data Index: 558542 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.2108. Min Act: -0.0001
Data Index: 1263533 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.0554. Min Act: -0.0001
Data Index: 460119 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.0532. Min Act: -0.0001
Data Index: 128206 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.0313. Min Act: -0.0001
Data Index: 979913 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2108. Min Range: -1.2108
Max Act: 0.9471. Min Act: -0.0001
Data Index: 299778 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2108. Min Range: -1.2108
Max Act: 0.9629. Min Act: -0.0001
Data Index: 625155 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.0759. Min Act: -0.0001
Data Index: 1333461 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.0013. Min Act: -0.0001
Data Index: 504642 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2108. Min Range: -1.2108
Max Act: 0.9450. Min Act: -0.0001
Data Index: 190794 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2108. Min Range: -1.2108
Max Act: 0.9235. Min Act: -0.0001
Data Index: 522754 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2108. Min Range: -1.2108
Max Act: 0.8366. Min Act: -0.0001
Data Index: 817931 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2108. Min Range: -1.2108
Max Act: 0.8801. Min Act: -0.0001
Data Index: 856700 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2108. Min Range: -1.2108
Max Act: 0.9029. Min Act: -0.0001
Data Index: 108244 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2108. Min Range: -1.2108
Max Act: 0.8955. Min Act: -0.0001
Data Index: 1256354 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2108. Min Range: -1.2108
Max Act: 1.0105. Min Act: -0.0001
Data Index: 933337 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2108. Min Range: -1.2108
Max Act: 0.9224. Min Act: -0.0001
Data Index: 1185276 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19