Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2099 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 3.0796. Min Range: -3.0796
Max Act: 3.0796. Min Act: -0.0000
Data Index: 1791403 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.7787. Min Act: -0.0000
Data Index: 1297250 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.7756. Min Act: -0.0000
Data Index: 5606 (The Pile)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.7189. Min Act: -0.0000
Data Index: 1324392 (The Pile)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.7060. Min Act: -0.0000
Data Index: 44498 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.5465. Min Act: -0.0000
Data Index: 1701226 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.4910. Min Act: -0.0000
Data Index: 1638100 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.7508. Min Act: -0.0000
Data Index: 930055 (The Pile)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.5823. Min Act: -0.0000
Data Index: 1160311 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.3994. Min Act: -0.0000
Data Index: 912513 (The Pile)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.3194. Min Act: -0.0000
Data Index: 1574548 (The Pile)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.3009. Min Act: -0.0000
Data Index: 972672 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.4254. Min Act: -0.0000
Data Index: 555895 (The Pile)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.2779. Min Act: -0.0000
Data Index: 1661578 (The Pile)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.2585. Min Act: -0.0000
Data Index: 225078 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.5193. Min Act: -0.0000
Data Index: 564113 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.3303. Min Act: -0.0000
Data Index: 244842 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.2171. Min Act: -0.0000
Data Index: 139950 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.3291. Min Act: -0.0000
Data Index: 882555 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0796. Min Range: -3.0796
Max Act: 2.1368. Min Act: -0.0000
Data Index: 1461479 (The Pile)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19