Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3285 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.4831. Min Act: -0.0001
Data Index: 1205926 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.4638. Min Act: -0.0001
Data Index: 955918 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.3754. Min Act: -0.0001
Data Index: 471819 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.2934. Min Act: -0.0001
Data Index: 958619 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.2902. Min Act: -0.0001
Data Index: 57122 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.2484. Min Act: -0.0001
Data Index: 926048 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.3201. Min Act: -0.0001
Data Index: 1508489 (Python Code)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.2901. Min Act: -0.0001
Data Index: 190823 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.2747. Min Act: -0.0001
Data Index: 498254 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.1600. Min Act: -0.0001
Data Index: 1148173 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4831. Min Range: -1.4831
Max Act: 0.9360. Min Act: -0.0001
Data Index: 806435 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.1351. Min Act: -0.0001
Data Index: 590860 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.2085. Min Act: -0.0001
Data Index: 724469 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.1966. Min Act: -0.0001
Data Index: 458240 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.1332. Min Act: -0.0001
Data Index: 467239 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.1798. Min Act: -0.0001
Data Index: 1290961 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.1104. Min Act: -0.0001
Data Index: 867804 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.1048. Min Act: -0.0001
Data Index: 1558972 (Python Code)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.1235. Min Act: -0.0001
Data Index: 648188 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4831. Min Range: -1.4831
Max Act: 1.1467. Min Act: -0.0001
Data Index: 232860 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19