Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1829 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.5570. Min Act: -0.0001
Data Index: 1492005 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.5231. Min Act: -0.0001
Data Index: 361643 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.5107. Min Act: -0.0001
Data Index: 508285 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4392. Min Act: -0.0001
Data Index: 644345 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4606. Min Act: -0.0001
Data Index: 1732111 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4428. Min Act: -0.0001
Data Index: 612493 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4360. Min Act: -0.0001
Data Index: 53065 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4282. Min Act: -0.0001
Data Index: 680636 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4421. Min Act: -0.0001
Data Index: 1733274 (The Pile)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4274. Min Act: -0.0001
Data Index: 1621697 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4311. Min Act: -0.0001
Data Index: 1272678 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4346. Min Act: -0.0001
Data Index: 1255910 (The Pile)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4195. Min Act: -0.0001
Data Index: 1402220 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4033. Min Act: -0.0001
Data Index: 898248 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.3962. Min Act: -0.0001
Data Index: 1936473 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4127. Min Act: -0.0001
Data Index: 75120 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4257. Min Act: -0.0001
Data Index: 1967892 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4219. Min Act: -0.0001
Data Index: 87847 (The Pile)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.3845. Min Act: -0.0001
Data Index: 1005316 (The Pile)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5570. Min Range: -0.5570
Max Act: 0.4190. Min Act: -0.0001
Data Index: 1623164 (The Pile)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19