Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3256 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.6829. Min Act: -0.0001
Data Index: 1961837 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5052. Min Act: -0.0001
Data Index: 925472 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5837. Min Act: -0.0001
Data Index: 1559361 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5231. Min Act: -0.0001
Data Index: 895975 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5642. Min Act: -0.0001
Data Index: 117839 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5520. Min Act: -0.0001
Data Index: 808008 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5730. Min Act: -0.0000
Data Index: 1142317 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.6056. Min Act: -0.0001
Data Index: 314737 (The Pile)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5140. Min Act: -0.0001
Data Index: 68337 (The Pile)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5603. Min Act: -0.0001
Data Index: 544996 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5458. Min Act: -0.0001
Data Index: 615606 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5424. Min Act: -0.0001
Data Index: 1797275 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5824. Min Act: -0.0001
Data Index: 560189 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.4992. Min Act: -0.0001
Data Index: 1058250 (The Pile)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.4675. Min Act: -0.0000
Data Index: 33171 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5500. Min Act: -0.0001
Data Index: 904634 (The Pile)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5116. Min Act: -0.0001
Data Index: 1268228 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5403. Min Act: -0.0001
Data Index: 14707 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.4665. Min Act: -0.0000
Data Index: 625758 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6829. Min Range: -0.6829
Max Act: 0.5152. Min Act: -0.0001
Data Index: 1881130 (The Pile)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19