Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 4882 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0478. Min Act: -0.0002
Data Index: 511987 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0372. Min Act: -0.0002
Data Index: 135465 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0357. Min Act: -0.0002
Data Index: 1424039 (The Pile)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0367. Min Act: -0.0002
Data Index: 763982 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0351. Min Act: -0.0002
Data Index: 1974855 (The Pile)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0319. Min Act: -0.0002
Data Index: 792895 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0327. Min Act: -0.0002
Data Index: 1915115 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0312. Min Act: -0.0002
Data Index: 669311 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0322. Min Act: -0.0002
Data Index: 965580 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0314. Min Act: -0.0001
Data Index: 925062 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0308. Min Act: -0.0001
Data Index: 1588342 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0308. Min Act: -0.0002
Data Index: 952862 (The Pile)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0309. Min Act: -0.0002
Data Index: 924242 (The Pile)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0298. Min Act: -0.0001
Data Index: 1806139 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0300. Min Act: -0.0002
Data Index: 1686544 (The Pile)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0305. Min Act: -0.0002
Data Index: 346204 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0299. Min Act: -0.0001
Data Index: 1584180 (The Pile)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0267. Min Act: -0.0002
Data Index: 418362 (The Pile)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0290. Min Act: -0.0002
Data Index: 56674 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0478. Min Range: -0.0478
Max Act: 0.0306. Min Act: -0.0002
Data Index: 411824 (The Pile)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19