Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3161 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.8959. Min Act: -0.0001
Data Index: 982634 (The Pile)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.5438. Min Act: -0.0001
Data Index: 1476583 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.4223. Min Act: -0.0001
Data Index: 1076564 (The Pile)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.3885. Min Act: -0.0001
Data Index: 887467 (The Pile)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.2665. Min Act: -0.0001
Data Index: 799575 (The Pile)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.3126. Min Act: -0.0001
Data Index: 1834478 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.1438. Min Act: -0.0001
Data Index: 398493 (The Pile)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.1648. Min Act: -0.0001
Data Index: 448763 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8959. Min Range: -1.8959
Max Act: 0.9874. Min Act: -0.0001
Data Index: 1427859 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.1440. Min Act: -0.0001
Data Index: 989179 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.1507. Min Act: -0.0001
Data Index: 751238 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.1701. Min Act: -0.0001
Data Index: 620262 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8959. Min Range: -1.8959
Max Act: 0.9888. Min Act: -0.0001
Data Index: 647245 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.2408. Min Act: -0.0001
Data Index: 1108886 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.1995. Min Act: -0.0001
Data Index: 322818 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.1345. Min Act: -0.0001
Data Index: 1199158 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8959. Min Range: -1.8959
Max Act: 0.9420. Min Act: -0.0001
Data Index: 537574 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.1409. Min Act: -0.0001
Data Index: 1032588 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.2767. Min Act: -0.0001
Data Index: 1170724 (The Pile)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8959. Min Range: -1.8959
Max Act: 1.2589. Min Act: -0.0001
Data Index: 891695 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19