Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1594 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.9373. Min Act: -0.0001
Data Index: 380758 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.9628. Min Act: -0.0001
Data Index: 1323972 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.9625. Min Act: -0.0001
Data Index: 292745 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8480. Min Act: -0.0001
Data Index: 119828 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.9720. Min Act: -0.0001
Data Index: 535215 (The Pile)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8979. Min Act: -0.0001
Data Index: 1921287 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8531. Min Act: -0.0001
Data Index: 401038 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8673. Min Act: -0.0001
Data Index: 1949334 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.9191. Min Act: -0.0001
Data Index: 425588 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8606. Min Act: -0.0001
Data Index: 1512854 (The Pile)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8105. Min Act: -0.0001
Data Index: 1803884 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8443. Min Act: -0.0001
Data Index: 374560 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.7931. Min Act: -0.0001
Data Index: 807795 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8323. Min Act: -0.0001
Data Index: 464925 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8627. Min Act: -0.0001
Data Index: 1702525 (The Pile)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.7642. Min Act: -0.0001
Data Index: 468479 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8743. Min Act: -0.0001
Data Index: 523404 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8134. Min Act: -0.0001
Data Index: 29549 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8148. Min Act: -0.0001
Data Index: 1846486 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9720. Min Range: -0.9720
Max Act: 0.8131. Min Act: -0.0001
Data Index: 311211 (The Pile)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19