Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2312 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.8787. Min Act: -0.0001
Data Index: 1079946 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.8070. Min Act: -0.0001
Data Index: 86700 (The Pile)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.6918. Min Act: -0.0001
Data Index: 1506717 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.6705. Min Act: -0.0001
Data Index: 392943 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.5324. Min Act: -0.0001
Data Index: 1250620 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.7101. Min Act: -0.0001
Data Index: 1778483 (The Pile)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.5707. Min Act: -0.0001
Data Index: 214043 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.5227. Min Act: -0.0001
Data Index: 372349 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.5725. Min Act: -0.0001
Data Index: 751193 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.4812. Min Act: -0.0001
Data Index: 230516 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.4159. Min Act: -0.0001
Data Index: 642679 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.4084. Min Act: -0.0001
Data Index: 908592 (The Pile)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.3588. Min Act: -0.0001
Data Index: 1767214 (The Pile)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.2863. Min Act: -0.0001
Data Index: 460487 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.3215. Min Act: -0.0001
Data Index: 878723 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.2806. Min Act: -0.0001
Data Index: 1336836 (The Pile)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.2645. Min Act: -0.0001
Data Index: 1647966 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.3242. Min Act: -0.0001
Data Index: 198192 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.2457. Min Act: -0.0001
Data Index: 27935 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8787. Min Range: -1.8787
Max Act: 1.4139. Min Act: -0.0001
Data Index: 289149 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19