Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2181 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.2712. Min Act: -0.0002
Data Index: 1441058 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.2532. Min Act: -0.0002
Data Index: 1071190 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.2460. Min Act: -0.0002
Data Index: 36468 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1814. Min Act: -0.0002
Data Index: 854901 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.2038. Min Act: -0.0002
Data Index: 1902838 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.2100. Min Act: -0.0002
Data Index: 1727081 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1734. Min Act: -0.0002
Data Index: 1267638 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1528. Min Act: -0.0002
Data Index: 659662 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1847. Min Act: -0.0002
Data Index: 1143755 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1303. Min Act: -0.0002
Data Index: 1462498 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1407. Min Act: -0.0002
Data Index: 1336755 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1109. Min Act: -0.0002
Data Index: 54173 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1397. Min Act: -0.0002
Data Index: 71375 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.0802. Min Act: -0.0002
Data Index: 346770 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.0953. Min Act: -0.0002
Data Index: 153507 (The Pile)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1038. Min Act: -0.0002
Data Index: 871737 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.1378. Min Act: -0.0002
Data Index: 1924736 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.0962. Min Act: -0.0002
Data Index: 1731632 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.0624. Min Act: -0.0002
Data Index: 372240 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2712. Min Range: -1.2712
Max Act: 1.0880. Min Act: -0.0002
Data Index: 1974269 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19