Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 4047 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4794. Min Act: -0.0001
Data Index: 1345362 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4139. Min Act: -0.0001
Data Index: 1329216 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4366. Min Act: -0.0001
Data Index: 1567230 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.6021. Min Act: -0.0001
Data Index: 1769948 (The Pile)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.6588. Min Act: -0.0001
Data Index: 1137757 (The Pile)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4000. Min Act: -0.0001
Data Index: 172732 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.5159. Min Act: -0.0001
Data Index: 1143795 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4758. Min Act: -0.0001
Data Index: 421327 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.2580. Min Act: -0.0001
Data Index: 1599168 (The Pile)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.3146. Min Act: -0.0001
Data Index: 79732 (The Pile)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.3205. Min Act: -0.0001
Data Index: 519149 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4120. Min Act: -0.0001
Data Index: 1157929 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.3788. Min Act: -0.0001
Data Index: 1934048 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4024. Min Act: -0.0001
Data Index: 1410575 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4520. Min Act: -0.0001
Data Index: 220603 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.3055. Min Act: -0.0001
Data Index: 596607 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.2681. Min Act: -0.0001
Data Index: 370859 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.2169. Min Act: -0.0001
Data Index: 1518241 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4344. Min Act: -0.0001
Data Index: 981731 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6588. Min Range: -1.6588
Max Act: 1.4687. Min Act: -0.0001
Data Index: 339106 (The Pile)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19