Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2865 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.5323. Min Act: -0.0001
Data Index: 569694 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.3817. Min Act: -0.0001
Data Index: 1737274 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.5148. Min Act: -0.0001
Data Index: 660916 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.4214. Min Act: -0.0001
Data Index: 350847 (The Pile)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.4639. Min Act: -0.0001
Data Index: 1860527 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.3141. Min Act: -0.0001
Data Index: 1799106 (The Pile)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.3567. Min Act: -0.0001
Data Index: 352831 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.2175. Min Act: -0.0001
Data Index: 291862 (The Pile)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.2927. Min Act: -0.0001
Data Index: 1964284 (The Pile)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.2122. Min Act: -0.0001
Data Index: 33185 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.1070. Min Act: -0.0001
Data Index: 860898 (The Pile)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.2175. Min Act: -0.0001
Data Index: 964895 (The Pile)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.1220. Min Act: -0.0001
Data Index: 1554237 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.1205. Min Act: -0.0001
Data Index: 759057 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.1868. Min Act: -0.0001
Data Index: 1509336 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.1814. Min Act: -0.0001
Data Index: 805198 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.0817. Min Act: -0.0001
Data Index: 857501 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.0475. Min Act: -0.0001
Data Index: 1207149 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.0705. Min Act: -0.0001
Data Index: 484210 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5323. Min Range: -1.5323
Max Act: 1.0109. Min Act: -0.0001
Data Index: 473251 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19