Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2491 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.5196. Min Act: -0.0002
Data Index: 214457 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.5264. Min Act: -0.0002
Data Index: 749346 (The Pile)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.5087. Min Act: -0.0002
Data Index: 206565 (The Pile)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.5049. Min Act: -0.0002
Data Index: 726793 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4807. Min Act: -0.0002
Data Index: 458229 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4909. Min Act: -0.0002
Data Index: 572781 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4887. Min Act: -0.0002
Data Index: 1457864 (The Pile)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4851. Min Act: -0.0002
Data Index: 1986782 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4855. Min Act: -0.0002
Data Index: 1749848 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4494. Min Act: -0.0002
Data Index: 108513 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4937. Min Act: -0.0002
Data Index: 1937135 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4782. Min Act: -0.0002
Data Index: 887329 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4625. Min Act: -0.0002
Data Index: 850681 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4740. Min Act: -0.0002
Data Index: 1460290 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4734. Min Act: -0.0002
Data Index: 819398 (The Pile)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4717. Min Act: -0.0002
Data Index: 1393444 (The Pile)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4694. Min Act: -0.0002
Data Index: 1434714 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.5010. Min Act: -0.0002
Data Index: 130350 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4868. Min Act: -0.0002
Data Index: 950596 (The Pile)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5264. Min Range: -0.5264
Max Act: 0.4563. Min Act: -0.0002
Data Index: 950561 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19