Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3385 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 3.0890. Min Range: -3.0890
Max Act: 3.0890. Min Act: -0.0000
Data Index: 851917 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.5309. Min Act: -0.0000
Data Index: 1208222 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.4437. Min Act: -0.0000
Data Index: 723648 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.6625. Min Act: -0.0000
Data Index: 535316 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.4921. Min Act: -0.0000
Data Index: 582366 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.5159. Min Act: -0.0000
Data Index: 492671 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.2331. Min Act: -0.0000
Data Index: 1298607 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0890. Min Range: -3.0890
Max Act: 1.9577. Min Act: -0.0000
Data Index: 493795 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.2879. Min Act: -0.0000
Data Index: 1807898 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.2738. Min Act: -0.0000
Data Index: 301314 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.2458. Min Act: -0.0000
Data Index: 608520 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.2000. Min Act: -0.0000
Data Index: 534928 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.0010. Min Act: -0.0000
Data Index: 867312 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.0897. Min Act: -0.0000
Data Index: 136360 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0890. Min Range: -3.0890
Max Act: 1.9189. Min Act: -0.0000
Data Index: 38840 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0890. Min Range: -3.0890
Max Act: 1.8911. Min Act: -0.0000
Data Index: 1174915 (The Pile)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.2037. Min Act: -0.0000
Data Index: 424486 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.0705. Min Act: -0.0000
Data Index: 377150 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.0256. Min Act: -0.0000
Data Index: 186294 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0890. Min Range: -3.0890
Max Act: 1.7647. Min Act: -0.0000
Data Index: 1649196 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19