Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 4704 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.6611. Min Act: -0.0000
Data Index: 771856 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.4246. Min Act: -0.0000
Data Index: 1865187 (The Pile)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.1234. Min Act: -0.0000
Data Index: 1999810 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.2086. Min Act: -0.0000
Data Index: 392592 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.0732. Min Act: -0.0000
Data Index: 581529 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.2723. Min Act: -0.0000
Data Index: 1901668 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.2088. Min Act: -0.0000
Data Index: 1844310 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.2226. Min Act: -0.0000
Data Index: 749803 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.1951. Min Act: -0.0000
Data Index: 960157 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.1797. Min Act: -0.0000
Data Index: 737795 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.1588. Min Act: -0.0000
Data Index: 1091578 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6611. Min Range: -2.6611
Max Act: 1.9232. Min Act: -0.0000
Data Index: 341395 (The Pile)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6611. Min Range: -2.6611
Max Act: 2.0202. Min Act: -0.0000
Data Index: 1789742 (The Pile)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6611. Min Range: -2.6611
Max Act: 1.8950. Min Act: -0.0000
Data Index: 476275 (The Pile)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6611. Min Range: -2.6611
Max Act: 1.8723. Min Act: -0.0000
Data Index: 511416 (The Pile)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6611. Min Range: -2.6611
Max Act: 1.9621. Min Act: -0.0000
Data Index: 43873 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6611. Min Range: -2.6611
Max Act: 1.9564. Min Act: -0.0000
Data Index: 1528102 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6611. Min Range: -2.6611
Max Act: 1.9597. Min Act: -0.0000
Data Index: 1376546 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6611. Min Range: -2.6611
Max Act: 1.8302. Min Act: -0.0000
Data Index: 1946700 (The Pile)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6611. Min Range: -2.6611
Max Act: 1.9257. Min Act: -0.0000
Data Index: 899825 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19