Model: SoLU Model: 2 Layers, 2944 Neurons per Layer
Dataset: The Pile
Neuron 1129 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')
Text #0
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0720. Min Act: -0.0002
Data Index: 1893204 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0485. Min Act: -0.0002
Data Index: 493009 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0470. Min Act: -0.0002
Data Index: 811569 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0465. Min Act: -0.0002
Data Index: 1375154 (The Pile)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0439. Min Act: -0.0002
Data Index: 1727836 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0442. Min Act: -0.0002
Data Index: 1090895 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0397. Min Act: -0.0002
Data Index: 479417 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0414. Min Act: -0.0002
Data Index: 429180 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0397. Min Act: -0.0002
Data Index: 1479042 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0383. Min Act: -0.0002
Data Index: 1766203 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0400. Min Act: -0.0002
Data Index: 1859749 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0394. Min Act: -0.0002
Data Index: 1017096 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0380. Min Act: -0.0002
Data Index: 911288 (The Pile)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0379. Min Act: -0.0002
Data Index: 630610 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0380. Min Act: -0.0002
Data Index: 150807 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0366. Min Act: -0.0002
Data Index: 194586 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0369. Min Act: -0.0002
Data Index: 266893 (The Pile)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0368. Min Act: -0.0002
Data Index: 645756 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0359. Min Act: -0.0002
Data Index: 1153299 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0720. Min Range: -0.0720
Max Act: 0.0373. Min Act: -0.0002
Data Index: 1952251 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19