Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1223 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 9.8815. Min Range: -9.8815
Max Act: 9.4158. Min Act: -0.0001
Data Index: 1882660 (The Pile)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8815. Min Range: -9.8815
Max Act: 8.8098. Min Act: -0.0001
Data Index: 807878 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8815. Min Range: -9.8815
Max Act: 9.1532. Min Act: -0.0001
Data Index: 463322 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8815. Min Range: -9.8815
Max Act: 8.0692. Min Act: -0.0001
Data Index: 796489 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8815. Min Range: -9.8815
Max Act: 8.9019. Min Act: -0.0001
Data Index: 1734489 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8815. Min Range: -9.8815
Max Act: 9.5255. Min Act: -0.0001
Data Index: 1358285 (The Pile)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8815. Min Range: -9.8815
Max Act: 8.8942. Min Act: -0.0001
Data Index: 1937396 (The Pile)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8815. Min Range: -9.8815
Max Act: 8.3214. Min Act: -0.0001
Data Index: 797146 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8815. Min Range: -9.8815
Max Act: 9.0003. Min Act: -0.0001
Data Index: 405994 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8815. Min Range: -9.8815
Max Act: 9.8815. Min Act: -0.0001
Data Index: 1983433 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8815. Min Range: -9.8815
Max Act: 8.2581. Min Act: -0.0001
Data Index: 628324 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8815. Min Range: -9.8815
Max Act: 7.6252. Min Act: -0.0001
Data Index: 743482 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8815. Min Range: -9.8815
Max Act: 9.5269. Min Act: -0.0001
Data Index: 929656 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8815. Min Range: -9.8815
Max Act: 8.1369. Min Act: -0.0001
Data Index: 1943710 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8815. Min Range: -9.8815
Max Act: 8.8245. Min Act: -0.0001
Data Index: 648884 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8815. Min Range: -9.8815
Max Act: 8.7116. Min Act: -0.0001
Data Index: 1039471 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8815. Min Range: -9.8815
Max Act: 9.7670. Min Act: -0.0001
Data Index: 377254 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8815. Min Range: -9.8815
Max Act: 7.8010. Min Act: -0.0001
Data Index: 1482562 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8815. Min Range: -9.8815
Max Act: 7.4570. Min Act: -0.0001
Data Index: 1252703 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8815. Min Range: -9.8815
Max Act: 7.9175. Min Act: -0.0001
Data Index: 600630 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19