Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 1059 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2769. Min Act: -0.0004
Data Index: 1589400 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2608. Min Act: -0.0004
Data Index: 90902 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2698. Min Act: -0.0004
Data Index: 1967389 (The Pile)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2532. Min Act: -0.0004
Data Index: 197137 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2702. Min Act: -0.0004
Data Index: 609137 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2303. Min Act: -0.0004
Data Index: 296283 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2357. Min Act: -0.0004
Data Index: 68611 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2328. Min Act: -0.0004
Data Index: 843272 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2293. Min Act: -0.0004
Data Index: 867384 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2282. Min Act: -0.0004
Data Index: 1929121 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2173. Min Act: -0.0004
Data Index: 545957 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2120. Min Act: -0.0004
Data Index: 631267 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2122. Min Act: -0.0004
Data Index: 517120 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2097. Min Act: -0.0004
Data Index: 958295 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2091. Min Act: -0.0004
Data Index: 1295592 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2188. Min Act: -0.0004
Data Index: 1830095 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2123. Min Act: -0.0004
Data Index: 203177 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2095. Min Act: -0.0004
Data Index: 916293 (The Pile)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2129. Min Act: -0.0004
Data Index: 564361 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2769. Min Range: -0.2769
Max Act: 0.2042. Min Act: -0.0004
Data Index: 1710405 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19