Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 726 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.4204. Min Act: -0.0001
Data Index: 22498 (The Pile)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.2646. Min Act: -0.0001
Data Index: 1670113 (The Pile)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.3663. Min Act: -0.0001
Data Index: 1387370 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.4888. Min Act: -0.0001
Data Index: 375561 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.1779. Min Act: -0.0001
Data Index: 1141275 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.5641. Min Act: -0.0001
Data Index: 299929 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.5390. Min Act: -0.0001
Data Index: 338712 (The Pile)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.2571. Min Act: -0.0001
Data Index: 975965 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.2572. Min Act: -0.0001
Data Index: 1006894 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.3952. Min Act: -0.0001
Data Index: 287938 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.2397. Min Act: -0.0001
Data Index: 1069057 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.3639. Min Act: -0.0001
Data Index: 240789 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.5209. Min Act: -0.0001
Data Index: 435308 (The Pile)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.3593. Min Act: -0.0001
Data Index: 347328 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.2276. Min Act: -0.0001
Data Index: 642491 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.3661. Min Act: -0.0001
Data Index: 769937 (The Pile)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5641. Min Range: -3.5641
Max Act: 2.9537. Min Act: -0.0001
Data Index: 139487 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.0610. Min Act: -0.0001
Data Index: 1001367 (The Pile)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.3505. Min Act: -0.0001
Data Index: 584342 (The Pile)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5641. Min Range: -3.5641
Max Act: 3.1747. Min Act: -0.0001
Data Index: 409512 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19