Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 536 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.1652. Min Range: -2.1652
Max Act: 2.1652. Min Act: -0.0001
Data Index: 708022 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.7777. Min Act: -0.0001
Data Index: 222096 (The Pile)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.7917. Min Act: -0.0001
Data Index: 1701743 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.8492. Min Act: -0.0001
Data Index: 1290205 (The Pile)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.8189. Min Act: -0.0001
Data Index: 324010 (The Pile)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.5910. Min Act: -0.0001
Data Index: 150546 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.4811. Min Act: -0.0001
Data Index: 1443006 (The Pile)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.2940. Min Act: -0.0001
Data Index: 173943 (The Pile)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.5793. Min Act: -0.0001
Data Index: 135517 (The Pile)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.5419. Min Act: -0.0001
Data Index: 649994 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.3527. Min Act: -0.0001
Data Index: 1074279 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.5249. Min Act: -0.0001
Data Index: 1647454 (The Pile)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.5642. Min Act: -0.0001
Data Index: 1632016 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.3937. Min Act: -0.0001
Data Index: 438663 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.3568. Min Act: -0.0001
Data Index: 1213551 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.4977. Min Act: -0.0001
Data Index: 521855 (The Pile)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.3622. Min Act: -0.0001
Data Index: 775473 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.5437. Min Act: -0.0001
Data Index: 21540 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.4496. Min Act: -0.0001
Data Index: 765880 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1652. Min Range: -2.1652
Max Act: 1.4526. Min Act: -0.0001
Data Index: 1257514 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19