Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2519 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.3944. Min Act: -0.0001
Data Index: 79452 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.1596. Min Act: -0.0001
Data Index: 1225524 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.1841. Min Act: -0.0001
Data Index: 722173 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.2377. Min Act: -0.0001
Data Index: 215981 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.1231. Min Act: -0.0001
Data Index: 17376 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.1745. Min Act: -0.0001
Data Index: 895325 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.1032. Min Act: -0.0001
Data Index: 1953578 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.0376. Min Act: -0.0001
Data Index: 1816517 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.0112. Min Act: -0.0001
Data Index: 1052938 (The Pile)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.0164. Min Act: -0.0001
Data Index: 1754083 (The Pile)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.0425. Min Act: -0.0001
Data Index: 627255 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3944. Min Range: -1.3944
Max Act: 0.9912. Min Act: -0.0001
Data Index: 244386 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.0070. Min Act: -0.0001
Data Index: 1102046 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3944. Min Range: -1.3944
Max Act: 0.9443. Min Act: -0.0001
Data Index: 593859 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.0407. Min Act: -0.0001
Data Index: 1265524 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3944. Min Range: -1.3944
Max Act: 0.9132. Min Act: -0.0001
Data Index: 1866403 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3944. Min Range: -1.3944
Max Act: 1.0308. Min Act: -0.0001
Data Index: 875477 (The Pile)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3944. Min Range: -1.3944
Max Act: 0.9385. Min Act: -0.0001
Data Index: 529961 (The Pile)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3944. Min Range: -1.3944
Max Act: 0.9523. Min Act: -0.0001
Data Index: 940323 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3944. Min Range: -1.3944
Max Act: 0.9312. Min Act: -0.0001
Data Index: 1178638 (The Pile)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19