Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2533 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 5.2571. Min Range: -5.2571
Max Act: 5.2571. Min Act: -0.0001
Data Index: 1757507 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.4001. Min Act: -0.0001
Data Index: 201374 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.2218. Min Act: -0.0001
Data Index: 283184 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.3379. Min Act: -0.0001
Data Index: 275137 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.9997. Min Act: -0.0001
Data Index: 1917027 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.9967. Min Act: -0.0001
Data Index: 160489 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.8109. Min Act: -0.0001
Data Index: 187218 (The Pile)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.3848. Min Act: -0.0001
Data Index: 331403 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.6836. Min Act: -0.0001
Data Index: 693193 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.6429. Min Act: -0.0001
Data Index: 1135641 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.6281. Min Act: -0.0001
Data Index: 1104973 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.6141. Min Act: -0.0001
Data Index: 768004 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.6224. Min Act: -0.0001
Data Index: 670050 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.9150. Min Act: -0.0001
Data Index: 159770 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.7967. Min Act: -0.0001
Data Index: 1788666 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.3787. Min Act: -0.0001
Data Index: 1818301 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.3776. Min Act: -0.0001
Data Index: 827258 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.2193. Min Act: -0.0001
Data Index: 1359764 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.8345. Min Act: -0.0001
Data Index: 1760572 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2571. Min Range: -5.2571
Max Act: 3.5004. Min Act: -0.0000
Data Index: 164942 (The Pile)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19