Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2471 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.6146. Min Act: -0.0000
Data Index: 1915184 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.5109. Min Act: -0.0000
Data Index: 968186 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.4642. Min Act: -0.0000
Data Index: 778115 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.3427. Min Act: -0.0000
Data Index: 1336788 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.2844. Min Act: -0.0000
Data Index: 857812 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.2410. Min Act: -0.0000
Data Index: 1156139 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.3040. Min Act: -0.0000
Data Index: 512758 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.2905. Min Act: -0.0000
Data Index: 889468 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.2247. Min Act: -0.0000
Data Index: 1900846 (The Pile)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.1798. Min Act: -0.0000
Data Index: 638201 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.2091. Min Act: -0.0000
Data Index: 1888668 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.0209. Min Act: -0.0000
Data Index: 1682741 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.1614. Min Act: -0.0000
Data Index: 646582 (The Pile)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.2273. Min Act: -0.0000
Data Index: 459470 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.1358. Min Act: -0.0000
Data Index: 659442 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.1317. Min Act: -0.0000
Data Index: 1294098 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.1806. Min Act: -0.0000
Data Index: 609190 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.1201. Min Act: -0.0000
Data Index: 69349 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6146. Min Range: -1.6146
Max Act: 0.9946. Min Act: -0.0000
Data Index: 813203 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6146. Min Range: -1.6146
Max Act: 1.1074. Min Act: -0.0000
Data Index: 130730 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19