Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2556 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.5487. Min Act: -0.0000
Data Index: 732002 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.5408. Min Act: -0.0000
Data Index: 188597 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.5185. Min Act: -0.0000
Data Index: 1511317 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.5020. Min Act: 0.0001
Data Index: 1525450 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4914. Min Act: -0.0000
Data Index: 142567 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4754. Min Act: -0.0000
Data Index: 710112 (The Pile)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4807. Min Act: -0.0000
Data Index: 907503 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4804. Min Act: -0.0000
Data Index: 708283 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4751. Min Act: -0.0000
Data Index: 765243 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4393. Min Act: -0.0000
Data Index: 617836 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4610. Min Act: -0.0000
Data Index: 920596 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4656. Min Act: -0.0000
Data Index: 1851761 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4463. Min Act: -0.0000
Data Index: 1614740 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4293. Min Act: -0.0000
Data Index: 90462 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4407. Min Act: -0.0000
Data Index: 718361 (The Pile)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4360. Min Act: -0.0000
Data Index: 1102526 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4229. Min Act: -0.0000
Data Index: 1653752 (The Pile)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4423. Min Act: 0.0000
Data Index: 637963 (The Pile)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4264. Min Act: -0.0000
Data Index: 1011008 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5487. Min Range: -0.5487
Max Act: 0.4367. Min Act: -0.0000
Data Index: 838847 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19