Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 658 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0424. Min Act: -0.0002
Data Index: 22774 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0346. Min Act: -0.0002
Data Index: 1428780 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0360. Min Act: -0.0002
Data Index: 1200215 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0344. Min Act: -0.0002
Data Index: 1354468 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0344. Min Act: -0.0002
Data Index: 372727 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0355. Min Act: -0.0002
Data Index: 1420208 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0356. Min Act: -0.0002
Data Index: 1744371 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 652373 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0357. Min Act: -0.0002
Data Index: 287037 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0357. Min Act: -0.0002
Data Index: 840715 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 156214 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 286238 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 443361 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 85860 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 749363 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 130041 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 578081 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 724783 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 800836 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0424. Min Range: -0.0424
Max Act: 0.0348. Min Act: -0.0002
Data Index: 745168 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19