Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 961 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.1535. Min Act: -0.0000
Data Index: 527831 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.2600. Min Act: -0.0000
Data Index: 833313 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.4725. Min Act: -0.0000
Data Index: 343247 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.4027. Min Act: -0.0000
Data Index: 1382511 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.0963. Min Act: -0.0000
Data Index: 1415473 (The Pile)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.1172. Min Act: -0.0000
Data Index: 1590263 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.0131. Min Act: -0.0000
Data Index: 674384 (The Pile)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.0952. Min Act: -0.0000
Data Index: 1657344 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4725. Min Range: -2.4725
Max Act: 1.8590. Min Act: -0.0000
Data Index: 467246 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.0680. Min Act: -0.0000
Data Index: 756411 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.1569. Min Act: -0.0000
Data Index: 250155 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.0452. Min Act: -0.0000
Data Index: 409623 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.0262. Min Act: -0.0000
Data Index: 191145 (The Pile)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4725. Min Range: -2.4725
Max Act: 1.9256. Min Act: -0.0000
Data Index: 1984328 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.1345. Min Act: -0.0000
Data Index: 37522 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.0188. Min Act: -0.0000
Data Index: 648101 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4725. Min Range: -2.4725
Max Act: 1.7927. Min Act: -0.0000
Data Index: 869594 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.1064. Min Act: -0.0000
Data Index: 338782 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4725. Min Range: -2.4725
Max Act: 2.0149. Min Act: -0.0000
Data Index: 1952404 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4725. Min Range: -2.4725
Max Act: 1.8652. Min Act: -0.0000
Data Index: 1185213 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19