Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1464 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.1845. Min Range: -1.1845
Max Act: 1.1845. Min Act: -0.0002
Data Index: 1655005 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1845. Min Range: -1.1845
Max Act: 1.0000. Min Act: -0.0002
Data Index: 560229 (The Pile)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.8981. Min Act: -0.0002
Data Index: 1461162 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.8278. Min Act: -0.0002
Data Index: 693249 (The Pile)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.8056. Min Act: -0.0002
Data Index: 214176 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.7311. Min Act: -0.0002
Data Index: 1715369 (The Pile)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.7714. Min Act: -0.0002
Data Index: 200479 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.7626. Min Act: -0.0002
Data Index: 1507267 (The Pile)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.7384. Min Act: -0.0002
Data Index: 630015 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.7212. Min Act: -0.0002
Data Index: 1371920 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6769. Min Act: -0.0002
Data Index: 693183 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6733. Min Act: -0.0002
Data Index: 1776357 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6860. Min Act: -0.0002
Data Index: 1501328 (The Pile)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6770. Min Act: -0.0002
Data Index: 1628755 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6824. Min Act: -0.0002
Data Index: 1978098 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6742. Min Act: -0.0002
Data Index: 700472 (The Pile)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6722. Min Act: -0.0002
Data Index: 954985 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6444. Min Act: -0.0002
Data Index: 541263 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6394. Min Act: -0.0002
Data Index: 318831 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1845. Min Range: -1.1845
Max Act: 0.6443. Min Act: -0.0002
Data Index: 1020162 (The Pile)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19